Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5926 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.5157. Min Act: -0.1700
Data Index: 7094634 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.4219. Min Act: -0.1700
Data Index: 650765 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.2969. Min Act: -0.1700
Data Index: 620270 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.2657. Min Act: -0.1700
Data Index: 11221 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.2032. Min Act: -0.1700
Data Index: 743739 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.1094. Min Act: -0.1700
Data Index: 4106746 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.0469. Min Act: -0.1700
Data Index: 4461848 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.0157. Min Act: -0.1700
Data Index: 4859327 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.0157. Min Act: -0.1700
Data Index: 3995718 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.0157. Min Act: -0.1700
Data Index: 5348936 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5157. Min Range: -6.5157
Max Act: 6.0157. Min Act: -0.1700
Data Index: 1819959 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.9844. Min Act: -0.1700
Data Index: 8675201 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.9844. Min Act: -0.1700
Data Index: 6853013 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.9844. Min Act: -0.1700
Data Index: 5106145 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.9844. Min Act: -0.1700
Data Index: 296077 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.9844. Min Act: -0.1700
Data Index: 7377458 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.9532. Min Act: -0.1700
Data Index: 3416417 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.9532. Min Act: -0.1700
Data Index: 4362381 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.8907. Min Act: -0.1700
Data Index: 2785153 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5157. Min Range: -6.5157
Max Act: 5.8907. Min Act: -0.1700
Data Index: 4204998 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19