Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5087 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1277. Min Range: -6.1277
Max Act: 6.1277. Min Act: -0.1700
Data Index: 4090994 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.8777. Min Act: -0.1700
Data Index: 7456740 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.8777. Min Act: -0.1700
Data Index: 806086 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.8777. Min Act: -0.1700
Data Index: 6361893 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.8465. Min Act: -0.1700
Data Index: 7462368 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.8152. Min Act: -0.1700
Data Index: 1657165 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7840. Min Act: -0.1700
Data Index: 4516041 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7840. Min Act: -0.1700
Data Index: 328209 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7840. Min Act: -0.1700
Data Index: 8398757 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7840. Min Act: -0.1700
Data Index: 3003588 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7527. Min Act: -0.1700
Data Index: 5556232 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7215. Min Act: -0.1700
Data Index: 3147628 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7215. Min Act: -0.1700
Data Index: 8509939 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.7215. Min Act: -0.1700
Data Index: 1311238 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.6902. Min Act: -0.1700
Data Index: 7143065 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.6902. Min Act: -0.1700
Data Index: 4355840 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.6902. Min Act: -0.1700
Data Index: 8368775 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.6902. Min Act: -0.1700
Data Index: 4669429 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.6590. Min Act: -0.1700
Data Index: 6299310 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1277. Min Range: -6.1277
Max Act: 5.6590. Min Act: -0.1700
Data Index: 4036612 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19