Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3911 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4800. Min Range: -8.4800
Max Act: 8.4800. Min Act: -0.1700
Data Index: 2104484 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4800. Min Range: -8.4800
Max Act: 8.3550. Min Act: -0.1700
Data Index: 8637283 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4800. Min Range: -8.4800
Max Act: 8.1050. Min Act: -0.1700
Data Index: 7130074 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.9800. Min Act: -0.1700
Data Index: 5602045 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.9175. Min Act: -0.1700
Data Index: 4305405 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.9175. Min Act: -0.1700
Data Index: 2322085 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.9175. Min Act: -0.1700
Data Index: 6723399 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.8550. Min Act: -0.1700
Data Index: 831188 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.8550. Min Act: -0.1700
Data Index: 2177430 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.8550. Min Act: -0.1700
Data Index: 1857966 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.7925. Min Act: -0.1700
Data Index: 6441493 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.7925. Min Act: -0.1700
Data Index: 8206280 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.7925. Min Act: -0.1700
Data Index: 283108 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.7925. Min Act: -0.1700
Data Index: 2994085 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.7300. Min Act: -0.1700
Data Index: 4371390 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.7300. Min Act: -0.1700
Data Index: 3766015 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.6675. Min Act: -0.1700
Data Index: 1198726 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.6050. Min Act: -0.1700
Data Index: 4582563 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.6675. Min Act: -0.1700
Data Index: 6257362 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4800. Min Range: -8.4800
Max Act: 7.6675. Min Act: -0.1700
Data Index: 4909440 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19