Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4579 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3920. Min Range: -2.3920
Max Act: 2.3593. Min Act: -0.1700
Data Index: 8752176 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3920. Min Range: -2.3920
Max Act: 2.3920. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.9229. Min Act: -0.1699
Data Index: 4993228 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.8461. Min Act: -0.1692
Data Index: 84592 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.8631. Min Act: -0.1697
Data Index: 230674 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.7622. Min Act: -0.1700
Data Index: 744548 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.7292. Min Act: -0.1700
Data Index: 6238541 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.7127. Min Act: -0.1700
Data Index: 717034 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.7127. Min Act: -0.1697
Data Index: 5487163 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.7046. Min Act: -0.1698
Data Index: 3193206 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6964. Min Act: -0.1700
Data Index: 1581735 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6883. Min Act: -0.1700
Data Index: 233253 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6883. Min Act: -0.1700
Data Index: 751899 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6801. Min Act: -0.1700
Data Index: 5487162 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6640. Min Act: -0.1700
Data Index: 1220356 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6640. Min Act: -0.1700
Data Index: 3858337 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6479. Min Act: -0.1700
Data Index: 6777827 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6399. Min Act: -0.1698
Data Index: 5692774 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.4704. Min Act: -0.1681
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3920. Min Range: -2.3920
Max Act: 0.6479. Min Act: -0.1700
Data Index: 1893099 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19