Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5926 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.9101. Min Act: -0.1700
Data Index: 173457 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.6914. Min Act: -0.1700
Data Index: 8494771 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.6601. Min Act: -0.1700
Data Index: 8759979 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.5664. Min Act: -0.1700
Data Index: 4518859 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.5664. Min Act: -0.1700
Data Index: 330117 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.5351. Min Act: -0.1700
Data Index: 6177376 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.5351. Min Act: -0.1700
Data Index: 5089025 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.4726. Min Act: -0.1700
Data Index: 3074281 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.4726. Min Act: -0.1700
Data Index: 5750110 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.4414. Min Act: -0.1700
Data Index: 3730991 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.4414. Min Act: -0.1700
Data Index: 5206247 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.3789. Min Act: -0.1700
Data Index: 6039306 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.3476. Min Act: -0.1700
Data Index: 4058738 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6310062 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.2851. Min Act: -0.1700
Data Index: 8112905 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.3164. Min Act: -0.1700
Data Index: 5646477 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.3164. Min Act: -0.1700
Data Index: 3291711 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.3164. Min Act: -0.1700
Data Index: 5903464 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.3164. Min Act: -0.1700
Data Index: 6828699 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9101. Min Range: -6.9101
Max Act: 6.2851. Min Act: -0.1700
Data Index: 145209 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19