Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5355 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.9042. Min Act: -0.1700
Data Index: 5019518 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.8730. Min Act: -0.1700
Data Index: 8621711 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.8417. Min Act: -0.1700
Data Index: 4949377 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.8105. Min Act: -0.1700
Data Index: 4671238 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.8105. Min Act: -0.1700
Data Index: 1400872 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.7792. Min Act: -0.1700
Data Index: 39851 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.7480. Min Act: -0.1700
Data Index: 5366335 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.7167. Min Act: -0.1700
Data Index: 8821945 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6855. Min Act: -0.1700
Data Index: 4861346 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6542. Min Act: -0.1700
Data Index: 3794273 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6542. Min Act: -0.1700
Data Index: 7883525 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6542. Min Act: -0.1700
Data Index: 8516016 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6542. Min Act: -0.1700
Data Index: 5360368 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6855. Min Act: -0.1700
Data Index: 6914926 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6542. Min Act: -0.1700
Data Index: 6137073 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6855. Min Act: -0.1700
Data Index: 1767039 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6230. Min Act: -0.1700
Data Index: 7455985 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6230. Min Act: -0.1700
Data Index: 1400470 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.5917. Min Act: -0.1700
Data Index: 4618229 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9042. Min Range: -4.9042
Max Act: 4.6230. Min Act: -0.1700
Data Index: 2660656 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19