Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.5121. Min Act: -0.1700
Data Index: 454655 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3983. Min Act: -0.1700
Data Index: 8263068 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3983. Min Act: -0.1700
Data Index: 7785797 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3819. Min Act: -0.1700
Data Index: 3737140 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3656. Min Act: -0.1700
Data Index: 6781042 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3492. Min Act: -0.1697
Data Index: 4170605 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3492. Min Act: -0.1700
Data Index: 3547790 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3328. Min Act: -0.1700
Data Index: 6229700 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3164. Min Act: -0.1700
Data Index: 5455063 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3328. Min Act: -0.1700
Data Index: 2579334 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3000. Min Act: -0.1700
Data Index: 2883902 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.3164. Min Act: -0.1700
Data Index: 5482761 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2835. Min Act: -0.1700
Data Index: 1851930 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2835. Min Act: -0.1700
Data Index: 7216923 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2670. Min Act: -0.1700
Data Index: 5360792 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2505. Min Act: -0.1700
Data Index: 2432654 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2505. Min Act: -0.1700
Data Index: 2981779 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2340. Min Act: -0.1700
Data Index: 7793296 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2340. Min Act: -0.1700
Data Index: 364839 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5121. Min Range: -2.5121
Max Act: 2.2340. Min Act: -0.1700
Data Index: 6132125 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19