Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.5355. Min Act: -0.1700
Data Index: 7716286 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.4417. Min Act: -0.1700
Data Index: 8032998 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.4417. Min Act: -0.1700
Data Index: 1278852 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.3792. Min Act: -0.1700
Data Index: 2162098 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.3792. Min Act: -0.1700
Data Index: 7555349 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.3480. Min Act: -0.1700
Data Index: 6223367 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.3167. Min Act: -0.1700
Data Index: 5397577 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.3167. Min Act: -0.1700
Data Index: 8817117 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.2855. Min Act: -0.1700
Data Index: 2931257 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.3167. Min Act: -0.1700
Data Index: 4957608 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.2542. Min Act: -0.1700
Data Index: 5601045 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.2542. Min Act: -0.1700
Data Index: 3483616 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.1917. Min Act: -0.1700
Data Index: 395113 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.2230. Min Act: -0.1700
Data Index: 2162423 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.1917. Min Act: -0.1700
Data Index: 3549591 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.1917. Min Act: -0.1700
Data Index: 4382507 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.1917. Min Act: -0.1700
Data Index: 6075345 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.1605. Min Act: -0.1700
Data Index: 5644285 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.1917. Min Act: -0.1700
Data Index: 7505797 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5355. Min Range: -5.5355
Max Act: 5.1292. Min Act: -0.1700
Data Index: 639164 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19