Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.5684. Min Act: -0.1700
Data Index: 985796 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.5059. Min Act: -0.1700
Data Index: 3530714 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.4746. Min Act: -0.1700
Data Index: 4233595 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3496. Min Act: -0.1700
Data Index: 4540643 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3183. Min Act: -0.1700
Data Index: 2340332 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2871. Min Act: -0.1700
Data Index: 1585672 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3183. Min Act: -0.1700
Data Index: 2749033 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.3183. Min Act: -0.1700
Data Index: 8741365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2558. Min Act: -0.1700
Data Index: 5986469 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2871. Min Act: -0.1700
Data Index: 2307931 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2558. Min Act: -0.1700
Data Index: 2352159 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2558. Min Act: -0.1700
Data Index: 1651648 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2558. Min Act: -0.1700
Data Index: 2062096 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2246. Min Act: -0.1700
Data Index: 152091 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2246. Min Act: -0.1700
Data Index: 5042922 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2246. Min Act: -0.1700
Data Index: 1511334 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2246. Min Act: -0.1700
Data Index: 1030012 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2246. Min Act: -0.1700
Data Index: 4890539 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2246. Min Act: -0.1700
Data Index: 3605114 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5684. Min Range: -4.5684
Max Act: 4.2246. Min Act: -0.1700
Data Index: 4665880 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19