Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 250 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.5407. Min Act: -0.1700
Data Index: 6660464 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.4470. Min Act: -0.1700
Data Index: 2170487 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.4157. Min Act: -0.1700
Data Index: 2143227 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.4157. Min Act: -0.1700
Data Index: 3801210 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.3845. Min Act: -0.1700
Data Index: 5023522 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.3532. Min Act: -0.1700
Data Index: 6227012 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.3532. Min Act: -0.1700
Data Index: 6301929 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.3532. Min Act: -0.1700
Data Index: 8049331 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.3220. Min Act: -0.1700
Data Index: 6913280 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.3220. Min Act: -0.1700
Data Index: 2719551 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.3220. Min Act: -0.1700
Data Index: 3508830 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2907. Min Act: -0.1700
Data Index: 6561465 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2907. Min Act: -0.1700
Data Index: 6660463 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2907. Min Act: -0.1700
Data Index: 8739603 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2907. Min Act: -0.1700
Data Index: 3327884 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2907. Min Act: -0.1700
Data Index: 1541599 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2907. Min Act: -0.1700
Data Index: 2388312 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2282. Min Act: -0.1700
Data Index: 6500491 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2595. Min Act: -0.1700
Data Index: 4010132 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5407. Min Range: -5.5407
Max Act: 5.2595. Min Act: -0.1700
Data Index: 593241 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19