Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.9737. Min Act: -0.1700
Data Index: 7512043 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.8487. Min Act: -0.1700
Data Index: 2825409 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.8174. Min Act: -0.1700
Data Index: 4512205 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.7862. Min Act: -0.1700
Data Index: 1967116 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.7549. Min Act: -0.1700
Data Index: 7959424 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.7237. Min Act: -0.1700
Data Index: 4486912 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.5987. Min Act: -0.1700
Data Index: 5266868 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.5987. Min Act: -0.1700
Data Index: 1856794 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.5362. Min Act: -0.1700
Data Index: 597204 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.5049. Min Act: -0.1700
Data Index: 3466503 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.4424. Min Act: -0.1700
Data Index: 6011749 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.4112. Min Act: -0.1700
Data Index: 6282970 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.4112. Min Act: -0.1700
Data Index: 177572 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.3799. Min Act: -0.1700
Data Index: 2647603 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.3799. Min Act: -0.1700
Data Index: 7345721 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.3174. Min Act: -0.1700
Data Index: 5562101 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.3174. Min Act: -0.1700
Data Index: 2647604 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.3174. Min Act: -0.1700
Data Index: 597200 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.2862. Min Act: -0.1700
Data Index: 2384076 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9737. Min Range: -6.9737
Max Act: 6.2862. Min Act: -0.1700
Data Index: 4099725 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19