Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.6274. Min Act: -0.1700
Data Index: 8771887 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.6274. Min Act: -0.1700
Data Index: 2105039 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.5336. Min Act: -0.1700
Data Index: 5000782 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.5336. Min Act: -0.1700
Data Index: 2298765 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.5024. Min Act: -0.1700
Data Index: 2949782 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.4399. Min Act: -0.1700
Data Index: 626308 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.4086. Min Act: -0.1700
Data Index: 2333768 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3461. Min Act: -0.1700
Data Index: 1787986 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3774. Min Act: -0.1700
Data Index: 6997926 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3461. Min Act: -0.1700
Data Index: 1815683 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3149. Min Act: -0.1700
Data Index: 4109532 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.2836. Min Act: -0.1700
Data Index: 2710895 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3149. Min Act: -0.1700
Data Index: 1526175 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3149. Min Act: -0.1700
Data Index: 8088644 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3149. Min Act: -0.1700
Data Index: 2387487 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3149. Min Act: -0.1700
Data Index: 941953 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.3149. Min Act: -0.1700
Data Index: 878447 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.2836. Min Act: -0.1700
Data Index: 6612071 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.2836. Min Act: -0.1700
Data Index: 816552 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6274. Min Range: -4.6274
Max Act: 4.2836. Min Act: -0.1700
Data Index: 5411548 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19