Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.4630. Min Act: -0.1700
Data Index: 37845 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.4943. Min Act: -0.1700
Data Index: 7690098 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.3693. Min Act: -0.1700
Data Index: 1594976 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.3380. Min Act: -0.1700
Data Index: 1435272 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.3068. Min Act: -0.1700
Data Index: 2328368 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.2443. Min Act: -0.1700
Data Index: 1827662 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.2443. Min Act: -0.1700
Data Index: 8024661 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.2443. Min Act: -0.1700
Data Index: 1708999 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.1193. Min Act: -0.1700
Data Index: 8541469 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0880. Min Act: -0.1700
Data Index: 425896 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.1193. Min Act: -0.1700
Data Index: 4153574 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0880. Min Act: -0.1700
Data Index: 4128331 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0880. Min Act: -0.1700
Data Index: 5523533 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0568. Min Act: -0.1700
Data Index: 670304 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0568. Min Act: -0.1700
Data Index: 670302 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0880. Min Act: -0.1700
Data Index: 1237070 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0568. Min Act: -0.1700
Data Index: 4756726 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4943. Min Range: -7.4943
Max Act: 7.0568. Min Act: -0.1700
Data Index: 5542345 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4943. Min Range: -7.4943
Max Act: 6.9943. Min Act: -0.1700
Data Index: 4542817 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4943. Min Range: -7.4943
Max Act: 6.9630. Min Act: -0.1700
Data Index: 2777785 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19