Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3469 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 6644206 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9881. Min Act: -0.1700
Data Index: 6830106 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9256. Min Act: -0.1700
Data Index: 3923634 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.9256. Min Act: -0.1700
Data Index: 3686931 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8943. Min Act: -0.1700
Data Index: 4905503 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8943. Min Act: -0.1700
Data Index: 10887 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8943. Min Act: -0.1700
Data Index: 8324248 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8006. Min Act: -0.1700
Data Index: 7790718 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8318. Min Act: -0.1700
Data Index: 7790717 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8318. Min Act: -0.1700
Data Index: 8545503 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8006. Min Act: -0.1700
Data Index: 667941 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.8006. Min Act: -0.1700
Data Index: 5975581 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7381. Min Act: -0.1700
Data Index: 2510750 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7693. Min Act: -0.1700
Data Index: 7598405 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7381. Min Act: -0.1700
Data Index: 7008989 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7381. Min Act: -0.1700
Data Index: 2704331 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.7068. Min Act: -0.1700
Data Index: 2263352 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 2290868 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6756. Min Act: -0.1700
Data Index: 1901070 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9881. Min Range: -4.9881
Max Act: 4.6443. Min Act: -0.1700
Data Index: 3905532 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19