Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 551 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.6918. Min Act: -0.1700
Data Index: 5093407 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.5668. Min Act: -0.1700
Data Index: 920944 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.5356. Min Act: -0.1700
Data Index: 115764 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.5043. Min Act: -0.1700
Data Index: 464188 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.5043. Min Act: -0.1700
Data Index: 7847047 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.3793. Min Act: -0.1700
Data Index: 3975882 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.3168. Min Act: -0.1700
Data Index: 5802856 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.2856. Min Act: -0.1700
Data Index: 4891273 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.2856. Min Act: -0.1700
Data Index: 3724218 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.2856. Min Act: -0.1700
Data Index: 5518383 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.2543. Min Act: -0.1700
Data Index: 3755165 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.2231. Min Act: -0.1700
Data Index: 2130152 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.2231. Min Act: -0.1700
Data Index: 5121580 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.1918. Min Act: -0.1700
Data Index: 7095128 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.1918. Min Act: -0.1700
Data Index: 1828259 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6461303 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.1606. Min Act: -0.1700
Data Index: 6341525 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.1606. Min Act: -0.1700
Data Index: 6296243 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.1606. Min Act: -0.1700
Data Index: 5109317 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6918. Min Range: -6.6918
Max Act: 6.1606. Min Act: -0.1700
Data Index: 4479004 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19