Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0240. Min Range: -7.0240
Max Act: 7.0240. Min Act: -0.1700
Data Index: 8755053 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.9928. Min Act: -0.1700
Data Index: 6697175 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8678. Min Act: -0.1700
Data Index: 1735810 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.8053. Min Act: -0.1700
Data Index: 6619453 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.7740. Min Act: -0.1700
Data Index: 8050123 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6803. Min Act: -0.1700
Data Index: 3281658 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6803. Min Act: -0.1700
Data Index: 941613 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6490. Min Act: -0.1700
Data Index: 1807225 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6803. Min Act: -0.1700
Data Index: 7194819 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6490. Min Act: -0.1700
Data Index: 2527779 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6490. Min Act: -0.1700
Data Index: 3010245 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6178. Min Act: -0.1700
Data Index: 450903 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.6178. Min Act: -0.1700
Data Index: 3648334 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.5865. Min Act: -0.1700
Data Index: 4712854 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.5553. Min Act: -0.1700
Data Index: 2241999 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.5553. Min Act: -0.1700
Data Index: 4556385 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.5553. Min Act: -0.1700
Data Index: 4490635 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.5240. Min Act: -0.1700
Data Index: 768113 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.5240. Min Act: -0.1700
Data Index: 4662994 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0240. Min Range: -7.0240
Max Act: 6.5240. Min Act: -0.1700
Data Index: 2137198 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19