Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2854. Min Range: -10.2854
Max Act: 10.2854. Min Act: -0.1700
Data Index: 3236506 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2854. Min Range: -10.2854
Max Act: 10.2854. Min Act: -0.1700
Data Index: 6409430 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2854. Min Range: -10.2854
Max Act: 10.0354. Min Act: -0.1700
Data Index: 4777391 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2854. Min Range: -10.2854
Max Act: 10.0979. Min Act: -0.1700
Data Index: 7125334 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.9104. Min Act: -0.1700
Data Index: 5103709 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.9104. Min Act: -0.1700
Data Index: 7815051 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.8479. Min Act: -0.1700
Data Index: 1552298 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.7854. Min Act: -0.1700
Data Index: 3668837 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.7229. Min Act: -0.1700
Data Index: 5998490 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.6604. Min Act: -0.1700
Data Index: 4022450 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.7229. Min Act: -0.1700
Data Index: 3885181 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.6604. Min Act: -0.1700
Data Index: 827944 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.5979. Min Act: -0.1700
Data Index: 5802296 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.5979. Min Act: -0.1700
Data Index: 8230349 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.5979. Min Act: -0.1700
Data Index: 8003072 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.6604. Min Act: -0.1700
Data Index: 5116552 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.5979. Min Act: -0.1700
Data Index: 434376 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.5979. Min Act: -0.1700
Data Index: 654758 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.5979. Min Act: -0.1700
Data Index: 5265 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2854. Min Range: -10.2854
Max Act: 9.5979. Min Act: -0.1700
Data Index: 7031386 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19