Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2500 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4899. Min Range: -8.4899
Max Act: 8.4899. Min Act: -0.1700
Data Index: 630389 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4899. Min Range: -8.4899
Max Act: 8.3649. Min Act: -0.1700
Data Index: 7940221 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4899. Min Range: -8.4899
Max Act: 8.3024. Min Act: -0.1700
Data Index: 436978 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4899. Min Range: -8.4899
Max Act: 8.3024. Min Act: -0.1700
Data Index: 706727 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4899. Min Range: -8.4899
Max Act: 8.1462. Min Act: -0.1700
Data Index: 8535945 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.9899. Min Act: -0.1700
Data Index: 4522719 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.9587. Min Act: -0.1700
Data Index: 69121 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.9274. Min Act: -0.1700
Data Index: 5858268 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.9274. Min Act: -0.1700
Data Index: 6156197 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.8649. Min Act: -0.1700
Data Index: 730480 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.8337. Min Act: -0.1700
Data Index: 7446192 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.8024. Min Act: -0.1700
Data Index: 3176621 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.7712. Min Act: -0.1700
Data Index: 6223802 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.7712. Min Act: -0.1700
Data Index: 885498 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.7712. Min Act: -0.1700
Data Index: 5959004 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.7399. Min Act: -0.1700
Data Index: 3602441 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.7087. Min Act: -0.1700
Data Index: 5079617 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.7087. Min Act: -0.1700
Data Index: 6799933 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.6462. Min Act: -0.1700
Data Index: 4116588 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4899. Min Range: -8.4899
Max Act: 7.6149. Min Act: -0.1700
Data Index: 6158540 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19