Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2260 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.4854. Min Act: -0.1700
Data Index: 2988884 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.4229. Min Act: -0.1700
Data Index: 6720162 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.3292. Min Act: -0.1700
Data Index: 5931160 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.2979. Min Act: -0.1700
Data Index: 7907537 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.2979. Min Act: -0.1700
Data Index: 2505617 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.2667. Min Act: -0.1700
Data Index: 1195545 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.2667. Min Act: -0.1700
Data Index: 7691714 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.2354. Min Act: -0.1700
Data Index: 6142719 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.1729. Min Act: -0.1700
Data Index: 2325792 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.1417. Min Act: -0.1700
Data Index: 629162 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.1104. Min Act: -0.1700
Data Index: 3787603 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.1104. Min Act: -0.1700
Data Index: 7866631 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.1104. Min Act: -0.1700
Data Index: 765675 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.0792. Min Act: -0.1700
Data Index: 7283722 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.0479. Min Act: -0.1700
Data Index: 6681018 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.0479. Min Act: -0.1700
Data Index: 8720989 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.0167. Min Act: -0.1700
Data Index: 4180037 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4854. Min Range: -6.4854
Max Act: 6.0167. Min Act: -0.1700
Data Index: 6318792 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4854. Min Range: -6.4854
Max Act: 5.9854. Min Act: -0.1700
Data Index: 5372682 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4854. Min Range: -6.4854
Max Act: 5.9542. Min Act: -0.1700
Data Index: 7101473 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19