Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4990 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.6290. Min Act: -0.1700
Data Index: 4411345 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.6290. Min Act: -0.1700
Data Index: 2581843 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.5040. Min Act: -0.1700
Data Index: 3712318 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.3165. Min Act: -0.1700
Data Index: 8034345 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.3165. Min Act: -0.1700
Data Index: 6265628 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.3165. Min Act: -0.1700
Data Index: 3077724 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.3165. Min Act: -0.1700
Data Index: 3264955 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.3165. Min Act: -0.1700
Data Index: 2985305 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.2852. Min Act: -0.1700
Data Index: 8167421 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.2540. Min Act: -0.1700
Data Index: 6097018 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.0352. Min Act: -0.1700
Data Index: 7161944 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.0352. Min Act: -0.1700
Data Index: 8005324 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.0352. Min Act: -0.1700
Data Index: 1812316 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6290. Min Range: -5.6290
Max Act: 5.0040. Min Act: -0.1700
Data Index: 2296183 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6290. Min Range: -5.6290
Max Act: 4.9415. Min Act: -0.1700
Data Index: 367311 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6290. Min Range: -5.6290
Max Act: 4.9102. Min Act: -0.1700
Data Index: 2788984 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6290. Min Range: -5.6290
Max Act: 4.9415. Min Act: -0.1700
Data Index: 1203372 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6290. Min Range: -5.6290
Max Act: 4.9102. Min Act: -0.1700
Data Index: 6348556 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6290. Min Range: -5.6290
Max Act: 4.9415. Min Act: -0.1700
Data Index: 4326839 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6290. Min Range: -5.6290
Max Act: 4.9727. Min Act: -0.1700
Data Index: 4882613 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19