Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2629 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.7103. Min Act: -0.1700
Data Index: 4244634 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5852. Min Act: -0.1700
Data Index: 3409724 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5538. Min Act: -0.1700
Data Index: 6360125 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5538. Min Act: -0.1700
Data Index: 7843998 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5538. Min Act: -0.1700
Data Index: 3409726 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5382. Min Act: -0.1700
Data Index: 1618906 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5382. Min Act: -0.1700
Data Index: 6626494 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5225. Min Act: -0.1700
Data Index: 4392005 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5225. Min Act: -0.1700
Data Index: 3409725 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4912. Min Act: -0.1700
Data Index: 7722607 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.5069. Min Act: -0.1700
Data Index: 1321209 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4912. Min Act: -0.1700
Data Index: 4730091 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4755. Min Act: -0.1700
Data Index: 6026331 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4755. Min Act: -0.1700
Data Index: 8500450 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4599. Min Act: -0.1700
Data Index: 4351803 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4442. Min Act: -0.1700
Data Index: 3784433 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4285. Min Act: -0.1700
Data Index: 76181 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4442. Min Act: -0.1700
Data Index: 6886553 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4285. Min Act: -0.1700
Data Index: 5480785 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7103. Min Range: -3.7103
Max Act: 3.4285. Min Act: -0.1700
Data Index: 3990726 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19