Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.9323. Min Act: -0.1700
Data Index: 2020331 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.8698. Min Act: -0.1700
Data Index: 5202976 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.8385. Min Act: -0.1700
Data Index: 3118612 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.7448. Min Act: -0.1700
Data Index: 4629079 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.7760. Min Act: -0.1700
Data Index: 5727802 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.7760. Min Act: -0.1700
Data Index: 6045362 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.7448. Min Act: -0.1700
Data Index: 3231117 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.6823. Min Act: -0.1700
Data Index: 3231118 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.6823. Min Act: -0.1700
Data Index: 1008854 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.5885. Min Act: -0.1700
Data Index: 5104814 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.5885. Min Act: -0.1700
Data Index: 336953 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.5260. Min Act: -0.1700
Data Index: 773062 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.5260. Min Act: -0.1700
Data Index: 1955590 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.4948. Min Act: -0.1700
Data Index: 3907653 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.4948. Min Act: -0.1700
Data Index: 419943 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.4010. Min Act: -0.1700
Data Index: 4076138 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.3698. Min Act: -0.1700
Data Index: 5121022 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.3698. Min Act: -0.1700
Data Index: 4387473 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.4010. Min Act: -0.1700
Data Index: 4071396 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9323. Min Range: -5.9323
Max Act: 5.3385. Min Act: -0.1700
Data Index: 8096020 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19