Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1637 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.8516. Min Act: -0.1700
Data Index: 1129611 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.8516. Min Act: -0.1700
Data Index: 2150115 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.8516. Min Act: -0.1700
Data Index: 4340154 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.8204. Min Act: -0.1700
Data Index: 846329 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.8204. Min Act: -0.1700
Data Index: 1921248 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.8204. Min Act: -0.1700
Data Index: 1280320 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7891. Min Act: -0.1700
Data Index: 2801115 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7579. Min Act: -0.1700
Data Index: 3903068 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7891. Min Act: -0.1700
Data Index: 6166847 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7891. Min Act: -0.1700
Data Index: 4833714 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7266. Min Act: -0.1700
Data Index: 326119 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7579. Min Act: -0.1700
Data Index: 5132352 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7266. Min Act: -0.1700
Data Index: 6251712 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.6954. Min Act: -0.1700
Data Index: 8027649 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7266. Min Act: -0.1700
Data Index: 7601225 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7266. Min Act: -0.1700
Data Index: 1540058 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7579. Min Act: -0.1700
Data Index: 5968096 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.7266. Min Act: -0.1700
Data Index: 5714999 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.6641. Min Act: -0.1700
Data Index: 5120020 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8516. Min Range: -4.8516
Max Act: 4.6954. Min Act: -0.1700
Data Index: 797823 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19