Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0202. Min Range: -4.0202
Max Act: 4.0202. Min Act: -0.1700
Data Index: 5142881 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.9577. Min Act: -0.1700
Data Index: 7481433 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.9265. Min Act: -0.1700
Data Index: 7862049 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.9265. Min Act: -0.1700
Data Index: 801135 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.9265. Min Act: -0.1700
Data Index: 7071587 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.9108. Min Act: -0.1700
Data Index: 5383100 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.9108. Min Act: -0.1700
Data Index: 1601582 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.9108. Min Act: -0.1700
Data Index: 5025667 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8796. Min Act: -0.1700
Data Index: 8134958 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8796. Min Act: -0.1700
Data Index: 4127772 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8639. Min Act: -0.1700
Data Index: 8177100 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8952. Min Act: -0.1700
Data Index: 5936038 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8639. Min Act: -0.1700
Data Index: 6944062 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8796. Min Act: -0.1700
Data Index: 3669936 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8639. Min Act: -0.1700
Data Index: 890164 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8483. Min Act: -0.1700
Data Index: 5142882 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8170. Min Act: -0.1700
Data Index: 1569257 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8326. Min Act: -0.1700
Data Index: 6119970 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8326. Min Act: -0.1700
Data Index: 1176343 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0202. Min Range: -4.0202
Max Act: 3.8326. Min Act: -0.1700
Data Index: 8481471 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19