Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 353 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.9534. Min Act: -0.1700
Data Index: 3780692 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.9190. Min Act: -0.1700
Data Index: 7695988 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.8422. Min Act: -0.1700
Data Index: 3581720 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.8507. Min Act: -0.1700
Data Index: 2614296 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.8422. Min Act: -0.1698
Data Index: 1190964 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.8338. Min Act: -0.1700
Data Index: 3002160 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7834. Min Act: -0.1700
Data Index: 1764066 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7667. Min Act: -0.1699
Data Index: 4407056 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7750. Min Act: -0.1700
Data Index: 2398938 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7750. Min Act: -0.1700
Data Index: 1126596 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7584. Min Act: -0.1699
Data Index: 6311221 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7584. Min Act: -0.1700
Data Index: 7782426 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7667. Min Act: -0.1700
Data Index: 6552484 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7418. Min Act: -0.1700
Data Index: 1830982 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7254. Min Act: -0.1698
Data Index: 7565937 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7254. Min Act: -0.1699
Data Index: 3858824 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7254. Min Act: -0.1667
Data Index: 6897734 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7336. Min Act: -0.1700
Data Index: 3976730 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7254. Min Act: -0.1700
Data Index: 8183536 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9534. Min Range: -0.9534
Max Act: 0.7172. Min Act: -0.1700
Data Index: 1231996 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19