Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.8379. Min Act: -0.1700
Data Index: 4891204 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.7753. Min Act: -0.1700
Data Index: 3885171 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.7440. Min Act: -0.1700
Data Index: 7406540 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.7128. Min Act: -0.1700
Data Index: 2394153 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.7440. Min Act: -0.1700
Data Index: 4557869 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.7440. Min Act: -0.1700
Data Index: 6083888 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.7128. Min Act: -0.1700
Data Index: 6911464 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.7128. Min Act: -0.1700
Data Index: 6227262 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6815. Min Act: -0.1700
Data Index: 8675020 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6815. Min Act: -0.1700
Data Index: 3861962 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6815. Min Act: -0.1700
Data Index: 8164645 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6502. Min Act: -0.1700
Data Index: 8675021 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6189. Min Act: -0.1700
Data Index: 8338188 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6502. Min Act: -0.1700
Data Index: 4313282 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6502. Min Act: -0.1700
Data Index: 6424056 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6502. Min Act: -0.1700
Data Index: 2449873 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6502. Min Act: -0.1700
Data Index: 3005683 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6502. Min Act: -0.1700
Data Index: 4926345 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6189. Min Act: -0.1700
Data Index: 4242426 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8379. Min Range: -3.8379
Max Act: 3.6189. Min Act: -0.1700
Data Index: 4503273 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19