Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5387 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 6138624 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 538818 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 3504599 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 8491385 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 5474386 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 3709594 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 3168845 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2639. Min Act: -0.1700
Data Index: 292195 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2639. Min Act: -0.1700
Data Index: 5485554 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 758528 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 6856010 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2639. Min Act: -0.1700
Data Index: 8014229 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 3440307 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 7766339 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 6856009 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 1207232 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 3253909 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1077. Min Act: -0.1700
Data Index: 2567386 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1389. Min Act: -0.1700
Data Index: 5934190 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1389. Min Act: -0.1700
Data Index: 6473010 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19