Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1759 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.2435. Min Act: -0.1700
Data Index: 2642078 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.2123. Min Act: -0.1700
Data Index: 8696628 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.2435. Min Act: -0.1700
Data Index: 4009507 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.1498. Min Act: -0.1700
Data Index: 6573128 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.1810. Min Act: -0.1700
Data Index: 1995065 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.1185. Min Act: -0.1700
Data Index: 5333828 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.0873. Min Act: -0.1700
Data Index: 1009434 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.0873. Min Act: -0.1700
Data Index: 2299464 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.0560. Min Act: -0.1700
Data Index: 2967931 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2435. Min Range: -5.2435
Max Act: 5.0248. Min Act: -0.1700
Data Index: 2932757 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.9935. Min Act: -0.1700
Data Index: 8400898 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.9310. Min Act: -0.1700
Data Index: 1300050 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.9623. Min Act: -0.1700
Data Index: 3875415 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.9623. Min Act: -0.1700
Data Index: 8658221 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.9310. Min Act: -0.1700
Data Index: 606975 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.9310. Min Act: -0.1700
Data Index: 7032256 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.8998. Min Act: -0.1700
Data Index: 7744566 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.8998. Min Act: -0.1700
Data Index: 6144329 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.8998. Min Act: -0.1700
Data Index: 7107016 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2435. Min Range: -5.2435
Max Act: 4.8685. Min Act: -0.1700
Data Index: 331613 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19