Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3995 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2797. Min Act: -0.1700
Data Index: 1707473 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2483. Min Act: -0.1700
Data Index: 7516740 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2797. Min Act: -0.1700
Data Index: 1707470 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2954. Min Act: -0.1700
Data Index: 3786575 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2797. Min Act: -0.1700
Data Index: 3255986 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2483. Min Act: -0.1700
Data Index: 265959 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2483. Min Act: -0.1700
Data Index: 2814191 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2169. Min Act: -0.1700
Data Index: 1047653 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2326. Min Act: -0.1700
Data Index: 4649264 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2011. Min Act: -0.1700
Data Index: 5036027 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.2169. Min Act: -0.1700
Data Index: 344065 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1854. Min Act: -0.1700
Data Index: 4653761 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1854. Min Act: -0.1700
Data Index: 1906330 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1854. Min Act: -0.1700
Data Index: 4772837 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1539. Min Act: -0.1700
Data Index: 3458944 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1539. Min Act: -0.1700
Data Index: 2674997 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1697. Min Act: -0.1700
Data Index: 8100739 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1539. Min Act: -0.1700
Data Index: 4922072 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1539. Min Act: -0.1700
Data Index: 4089918 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2954. Min Range: -3.2954
Max Act: 3.1382. Min Act: -0.1700
Data Index: 4320016 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19