Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.9498. Min Act: -0.1700
Data Index: 8585508 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.8248. Min Act: -0.1700
Data Index: 495088 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.6998. Min Act: -0.1700
Data Index: 4184747 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.4498. Min Act: -0.1700
Data Index: 5683696 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.4498. Min Act: -0.1700
Data Index: 6380999 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.4185. Min Act: -0.1700
Data Index: 8822611 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.4185. Min Act: -0.1700
Data Index: 4920038 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.4498. Min Act: -0.1700
Data Index: 2598029 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.3873. Min Act: -0.1700
Data Index: 1157251 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.3560. Min Act: -0.1700
Data Index: 3321273 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.3560. Min Act: -0.1700
Data Index: 3881240 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.3248. Min Act: -0.1700
Data Index: 2994797 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.3248. Min Act: -0.1700
Data Index: 5433609 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.2935. Min Act: -0.1700
Data Index: 2718344 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.2623. Min Act: -0.1700
Data Index: 7384142 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.2310. Min Act: -0.1700
Data Index: 3902974 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.2310. Min Act: -0.1700
Data Index: 6162911 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.2310. Min Act: -0.1700
Data Index: 6350876 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.2310. Min Act: -0.1700
Data Index: 6169538 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9498. Min Range: -5.9498
Max Act: 5.2310. Min Act: -0.1700
Data Index: 6218896 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19