Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3558 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3981. Min Range: -6.3981
Max Act: 6.3981. Min Act: -0.1700
Data Index: 4538818 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3981. Min Range: -6.3981
Max Act: 6.0543. Min Act: -0.1700
Data Index: 6151681 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.9293. Min Act: -0.1700
Data Index: 2506674 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8356. Min Act: -0.1700
Data Index: 7539113 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8043. Min Act: -0.1700
Data Index: 1778607 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8043. Min Act: -0.1700
Data Index: 1696397 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.8043. Min Act: -0.1700
Data Index: 3962458 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7731. Min Act: -0.1700
Data Index: 1549276 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7418. Min Act: -0.1700
Data Index: 4094044 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7106. Min Act: -0.1700
Data Index: 5238698 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7106. Min Act: -0.1700
Data Index: 2399640 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6793. Min Act: -0.1700
Data Index: 3436103 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.7106. Min Act: -0.1700
Data Index: 8343877 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6793. Min Act: -0.1700
Data Index: 7906005 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6793. Min Act: -0.1700
Data Index: 3559797 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6481. Min Act: -0.1700
Data Index: 4735868 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6481. Min Act: -0.1700
Data Index: 6795942 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6793. Min Act: -0.1700
Data Index: 4989431 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6793. Min Act: -0.1700
Data Index: 3276070 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3981. Min Range: -6.3981
Max Act: 5.6793. Min Act: -0.1700
Data Index: 1884311 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19