Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 749 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.8342. Min Act: -0.1695
Data Index: 6605064 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.8084. Min Act: -0.1700
Data Index: 4201428 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7998. Min Act: -0.1700
Data Index: 825834 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7826. Min Act: -0.1700
Data Index: 3397038 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7740. Min Act: -0.1700
Data Index: 8135742 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7654. Min Act: -0.1700
Data Index: 7215225 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7654. Min Act: -0.1700
Data Index: 2312186 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7395. Min Act: -0.1698
Data Index: 6851466 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7567. Min Act: -0.1699
Data Index: 7463035 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7395. Min Act: -0.1700
Data Index: 3064225 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7481. Min Act: -0.1700
Data Index: 3834274 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7395. Min Act: -0.1700
Data Index: 3306333 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7308. Min Act: -0.1700
Data Index: 6851467 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7308. Min Act: -0.1699
Data Index: 5077424 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7222. Min Act: -0.1700
Data Index: 4974642 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7048. Min Act: -0.1700
Data Index: 5629412 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7048. Min Act: -0.1700
Data Index: 4323752 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7135. Min Act: -0.1700
Data Index: 6827756 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7135. Min Act: -0.1686
Data Index: 1308457 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8342. Min Range: -1.8342
Max Act: 1.7135. Min Act: -0.1687
Data Index: 4554283 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19