Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.7098. Min Act: -0.1700
Data Index: 1663846 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.7098. Min Act: -0.1700
Data Index: 5633713 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.6473. Min Act: -0.1700
Data Index: 3675463 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.5223. Min Act: -0.1700
Data Index: 6942037 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.5223. Min Act: -0.1700
Data Index: 2187024 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.4598. Min Act: -0.1700
Data Index: 1320293 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.3973. Min Act: -0.1700
Data Index: 7508307 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.3348. Min Act: -0.1700
Data Index: 8178739 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2098. Min Act: -0.1700
Data Index: 7084730 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.3348. Min Act: -0.1700
Data Index: 1625189 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2723. Min Act: -0.1700
Data Index: 7274538 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2098. Min Act: -0.1700
Data Index: 534714 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2098. Min Act: -0.1700
Data Index: 1014341 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.1473. Min Act: -0.1700
Data Index: 4028804 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2098. Min Act: -0.1700
Data Index: 2110112 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2098. Min Act: -0.1700
Data Index: 4758121 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2098. Min Act: -0.1700
Data Index: 2434311 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.2098. Min Act: -0.1700
Data Index: 1859697 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.1473. Min Act: -0.1700
Data Index: 2392778 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7098. Min Range: -10.7098
Max Act: 10.1473. Min Act: -0.1700
Data Index: 5956580 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19