Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6367 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.6896. Min Act: -0.1700
Data Index: 8013913 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.6896. Min Act: -0.1700
Data Index: 997522 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.6584. Min Act: -0.1700
Data Index: 5075202 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.5334. Min Act: -0.1700
Data Index: 5464586 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.5334. Min Act: -0.1700
Data Index: 3637342 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.5334. Min Act: -0.1700
Data Index: 2717048 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.5021. Min Act: -0.1700
Data Index: 6704469 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.4709. Min Act: -0.1700
Data Index: 1406293 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.4396. Min Act: -0.1700
Data Index: 8675809 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.4396. Min Act: -0.1700
Data Index: 7589581 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.4084. Min Act: -0.1700
Data Index: 1317200 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.4084. Min Act: -0.1700
Data Index: 3827087 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.3771. Min Act: -0.1700
Data Index: 3236493 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.3459. Min Act: -0.1700
Data Index: 6510469 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.3459. Min Act: -0.1700
Data Index: 3063253 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.3771. Min Act: -0.1700
Data Index: 5836170 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.3146. Min Act: -0.1700
Data Index: 107798 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.2834. Min Act: -0.1700
Data Index: 6569207 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.2834. Min Act: -0.1700
Data Index: 1487614 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6896. Min Range: -4.6896
Max Act: 4.2834. Min Act: -0.1700
Data Index: 2089063 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19