Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2614 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.8511. Min Act: -0.1700
Data Index: 2122629 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.7261. Min Act: -0.1700
Data Index: 4681611 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.7574. Min Act: -0.1700
Data Index: 5225464 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.7261. Min Act: -0.1700
Data Index: 1339662 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.7261. Min Act: -0.1700
Data Index: 1609832 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.6636. Min Act: -0.1700
Data Index: 5419900 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.6324. Min Act: -0.1700
Data Index: 1313942 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.6011. Min Act: -0.1700
Data Index: 8623481 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.5386. Min Act: -0.1700
Data Index: 7924466 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.5386. Min Act: -0.1700
Data Index: 8738107 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.5386. Min Act: -0.1700
Data Index: 2675656 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.5074. Min Act: -0.1700
Data Index: 7924465 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.4761. Min Act: -0.1700
Data Index: 3057955 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.4449. Min Act: -0.1700
Data Index: 6899205 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.4136. Min Act: -0.1700
Data Index: 1194107 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.4136. Min Act: -0.1700
Data Index: 2602781 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.4136. Min Act: -0.1700
Data Index: 6210099 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.3824. Min Act: -0.1700
Data Index: 6593197 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.3511. Min Act: -0.1700
Data Index: 2357225 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8511. Min Range: -6.8511
Max Act: 6.3511. Min Act: -0.1700
Data Index: 6137785 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19