Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 41 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.6199. Min Act: -0.1700
Data Index: 2035459 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.6039. Min Act: -0.1700
Data Index: 778378 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.5394. Min Act: -0.1700
Data Index: 8790918 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.5394. Min Act: -0.1700
Data Index: 1890551 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.5394. Min Act: -0.1700
Data Index: 7182414 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.5070. Min Act: -0.1700
Data Index: 3627283 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.5070. Min Act: -0.1700
Data Index: 4965712 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.5070. Min Act: -0.1700
Data Index: 7924983 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4746. Min Act: -0.1700
Data Index: 3292341 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4908. Min Act: -0.1700
Data Index: 7950052 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4908. Min Act: -0.1700
Data Index: 1402548 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4908. Min Act: -0.1700
Data Index: 5792560 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4908. Min Act: -0.1700
Data Index: 4508570 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.5070. Min Act: -0.1700
Data Index: 3369037 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4908. Min Act: -0.1700
Data Index: 3357267 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4746. Min Act: -0.1700
Data Index: 3632998 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4746. Min Act: -0.1700
Data Index: 1133449 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4746. Min Act: -0.1700
Data Index: 6713054 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4746. Min Act: -0.1700
Data Index: 6102748 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6199. Min Range: -2.6199
Max Act: 2.4746. Min Act: -0.1700
Data Index: 6969208 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19