Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0443. Min Range: -5.0443
Max Act: 5.0443. Min Act: -0.1700
Data Index: 7913902 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.9193. Min Act: -0.1700
Data Index: 4203618 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.9193. Min Act: -0.1700
Data Index: 6883161 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.8880. Min Act: -0.1700
Data Index: 7167877 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.8880. Min Act: -0.1700
Data Index: 205481 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.8880. Min Act: -0.1700
Data Index: 4601233 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.8255. Min Act: -0.1700
Data Index: 6643152 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.8255. Min Act: -0.1700
Data Index: 6613466 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.8255. Min Act: -0.1700
Data Index: 3834216 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.8255. Min Act: -0.1700
Data Index: 1962883 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7943. Min Act: -0.1700
Data Index: 152501 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7943. Min Act: -0.1700
Data Index: 458572 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7943. Min Act: -0.1700
Data Index: 6800822 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7943. Min Act: -0.1700
Data Index: 7956249 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7630. Min Act: -0.1700
Data Index: 1082489 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7943. Min Act: -0.1700
Data Index: 5603564 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7630. Min Act: -0.1700
Data Index: 4477059 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7630. Min Act: -0.1700
Data Index: 3765820 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7630. Min Act: -0.1700
Data Index: 7086490 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0443. Min Range: -5.0443
Max Act: 4.7005. Min Act: -0.1700
Data Index: 985661 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19