Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.8728. Min Act: -0.1700
Data Index: 3671390 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.8103. Min Act: -0.1700
Data Index: 3176644 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.6540. Min Act: -0.1700
Data Index: 8200976 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.5290. Min Act: -0.1700
Data Index: 3847022 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4978. Min Act: -0.1700
Data Index: 1165546 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4665. Min Act: -0.1700
Data Index: 2826172 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4665. Min Act: -0.1700
Data Index: 3151746 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4665. Min Act: -0.1700
Data Index: 38958 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4353. Min Act: -0.1700
Data Index: 3378293 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.4353. Min Act: -0.1700
Data Index: 4710617 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3728. Min Act: -0.1700
Data Index: 4869462 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3728. Min Act: -0.1700
Data Index: 6954246 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3415. Min Act: -0.1700
Data Index: 3988510 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3103. Min Act: -0.1700
Data Index: 1089401 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3415. Min Act: -0.1700
Data Index: 2784644 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3415. Min Act: -0.1700
Data Index: 476622 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3415. Min Act: -0.1700
Data Index: 8424899 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3103. Min Act: -0.1700
Data Index: 2802548 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3103. Min Act: -0.1700
Data Index: 255936 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8728. Min Range: -6.8728
Max Act: 6.3103. Min Act: -0.1700
Data Index: 6820580 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19