Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2499 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0244. Min Range: -6.0244
Max Act: 6.0244. Min Act: -0.1700
Data Index: 921587 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0244. Min Range: -6.0244
Max Act: 6.0244. Min Act: -0.1700
Data Index: 921583 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.9306. Min Act: -0.1700
Data Index: 5849994 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.8994. Min Act: -0.1700
Data Index: 5058348 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.8681. Min Act: -0.1700
Data Index: 8707174 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.8369. Min Act: -0.1700
Data Index: 4982515 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.7744. Min Act: -0.1700
Data Index: 4986525 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.7744. Min Act: -0.1700
Data Index: 1997241 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.7744. Min Act: -0.1700
Data Index: 8041396 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.8056. Min Act: -0.1700
Data Index: 1384967 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1494812 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1439644 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.6806. Min Act: -0.1700
Data Index: 3628589 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.6806. Min Act: -0.1700
Data Index: 392351 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1062027 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.6806. Min Act: -0.1700
Data Index: 1086162 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.6494. Min Act: -0.1700
Data Index: 3401086 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.6494. Min Act: -0.1700
Data Index: 7113276 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.6494. Min Act: -0.1700
Data Index: 1796638 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0244. Min Range: -6.0244
Max Act: 5.5869. Min Act: -0.1700
Data Index: 256999 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19