Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.6549. Min Act: -0.1700
Data Index: 8632556 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.6549. Min Act: -0.1700
Data Index: 4175539 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.6236. Min Act: -0.1700
Data Index: 7903145 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.6236. Min Act: -0.1700
Data Index: 2196535 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.5611. Min Act: -0.1700
Data Index: 7318885 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.4986. Min Act: -0.1700
Data Index: 7594457 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.4674. Min Act: -0.1700
Data Index: 1417404 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.4986. Min Act: -0.1700
Data Index: 504726 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.4049. Min Act: -0.1700
Data Index: 4595524 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.4049. Min Act: -0.1700
Data Index: 7654883 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.3736. Min Act: -0.1700
Data Index: 5319315 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.3424. Min Act: -0.1700
Data Index: 8496677 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.3111. Min Act: -0.1700
Data Index: 5658213 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.3111. Min Act: -0.1700
Data Index: 7138974 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.3111. Min Act: -0.1700
Data Index: 6902417 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.3111. Min Act: -0.1700
Data Index: 7849320 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.2799. Min Act: -0.1700
Data Index: 3511065 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.2174. Min Act: -0.1700
Data Index: 3691503 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.2486. Min Act: -0.1700
Data Index: 2370454 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6549. Min Range: -7.6549
Max Act: 7.2174. Min Act: -0.1700
Data Index: 5511973 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19