Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.6378. Min Act: -0.1700
Data Index: 155510 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.2628. Min Act: -0.1700
Data Index: 8171430 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.3253. Min Act: -0.1700
Data Index: 2073368 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.3253. Min Act: -0.1700
Data Index: 6169694 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.2628. Min Act: -0.1700
Data Index: 3342803 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.1378. Min Act: -0.1700
Data Index: 7771309 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.2003. Min Act: -0.1700
Data Index: 6562487 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.2003. Min Act: -0.1700
Data Index: 966020 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.1378. Min Act: -0.1700
Data Index: 4160391 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0753. Min Act: -0.1700
Data Index: 922783 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0753. Min Act: -0.1700
Data Index: 2708531 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0128. Min Act: -0.1700
Data Index: 3502285 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0753. Min Act: -0.1700
Data Index: 7634626 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0753. Min Act: -0.1700
Data Index: 5678631 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0128. Min Act: -0.1700
Data Index: 4208762 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0128. Min Act: -0.1700
Data Index: 4865939 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0753. Min Act: -0.1700
Data Index: 7506668 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0128. Min Act: -0.1700
Data Index: 1639559 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0128. Min Act: -0.1700
Data Index: 2723707 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6378. Min Range: -12.6378
Max Act: 12.0753. Min Act: -0.1700
Data Index: 180923 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19