Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.8319. Min Act: -0.1700
Data Index: 4610031 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.7694. Min Act: -0.1700
Data Index: 7247523 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.7381. Min Act: -0.1700
Data Index: 741345 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.6756. Min Act: -0.1700
Data Index: 6069823 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.6131. Min Act: -0.1700
Data Index: 5674665 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.6444. Min Act: -0.1700
Data Index: 7910609 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5819. Min Act: -0.1700
Data Index: 3773770 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.6131. Min Act: -0.1700
Data Index: 7572622 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5506. Min Act: -0.1700
Data Index: 2175450 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4256. Min Act: -0.1700
Data Index: 4559849 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5819. Min Act: -0.1700
Data Index: 6904104 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5506. Min Act: -0.1700
Data Index: 3927708 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4569. Min Act: -0.1700
Data Index: 1129109 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5506. Min Act: -0.1700
Data Index: 3185846 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5819. Min Act: -0.1700
Data Index: 1904262 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5506. Min Act: -0.1700
Data Index: 106344 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5194. Min Act: -0.1700
Data Index: 718563 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5506. Min Act: -0.1700
Data Index: 5437951 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.5194. Min Act: -0.1700
Data Index: 1338266 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8319. Min Range: -5.8319
Max Act: 5.4569. Min Act: -0.1700
Data Index: 2375178 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19