Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.7005. Min Act: -0.1700
Data Index: 888531 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.7005. Min Act: -0.1700
Data Index: 2460077 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.5130. Min Act: -0.1700
Data Index: 999892 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.2630. Min Act: -0.1700
Data Index: 246938 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.1380. Min Act: -0.1700
Data Index: 7659553 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.0755. Min Act: -0.1700
Data Index: 3290163 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.0130. Min Act: -0.1700
Data Index: 3773468 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.0130. Min Act: -0.1700
Data Index: 8104088 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.0755. Min Act: -0.1700
Data Index: 5121213 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.0130. Min Act: -0.1700
Data Index: 2100002 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7005. Min Range: -9.7005
Max Act: 9.0130. Min Act: -0.1700
Data Index: 2628982 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8880. Min Act: -0.1700
Data Index: 581135 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8880. Min Act: -0.1700
Data Index: 43372 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8880. Min Act: -0.1700
Data Index: 4383910 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8880. Min Act: -0.1700
Data Index: 1320402 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8255. Min Act: -0.1700
Data Index: 1312418 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8255. Min Act: -0.1700
Data Index: 4230362 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8255. Min Act: -0.1700
Data Index: 645753 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.8255. Min Act: -0.1700
Data Index: 4206513 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7005. Min Range: -9.7005
Max Act: 8.7630. Min Act: -0.1700
Data Index: 5265404 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19