Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.8005. Min Act: -0.1700
Data Index: 1958754 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.7380. Min Act: -0.1700
Data Index: 6106813 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.7380. Min Act: -0.1700
Data Index: 4461101 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.6755. Min Act: -0.1700
Data Index: 898923 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.6755. Min Act: -0.1700
Data Index: 5362637 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.6755. Min Act: -0.1700
Data Index: 6088516 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.6755. Min Act: -0.1700
Data Index: 5273794 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.6130. Min Act: -0.1700
Data Index: 7688727 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.6130. Min Act: -0.1700
Data Index: 8508589 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.5505. Min Act: -0.1700
Data Index: 2755364 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.5505. Min Act: -0.1700
Data Index: 1237417 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4880. Min Act: -0.1700
Data Index: 838319 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4880. Min Act: -0.1700
Data Index: 4168919 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4880. Min Act: -0.1700
Data Index: 4187509 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4255. Min Act: -0.1700
Data Index: 7527898 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4255. Min Act: -0.1700
Data Index: 7935192 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4880. Min Act: -0.1700
Data Index: 5650067 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4255. Min Act: -0.1700
Data Index: 8291937 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.4255. Min Act: -0.1700
Data Index: 393979 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8005. Min Range: -9.8005
Max Act: 9.3630. Min Act: -0.1700
Data Index: 5018374 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19