Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.7433. Min Act: -0.1700
Data Index: 7493112 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.5242. Min Act: -0.1700
Data Index: 71172 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.4145. Min Act: -0.1700
Data Index: 7710819 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3832. Min Act: -0.1700
Data Index: 4642944 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3675. Min Act: -0.1700
Data Index: 136840 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3675. Min Act: -0.1700
Data Index: 5648798 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3518. Min Act: -0.1700
Data Index: 324617 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3361. Min Act: -0.1700
Data Index: 3678542 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3204. Min Act: -0.1700
Data Index: 7039669 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3361. Min Act: -0.1700
Data Index: 1549759 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3518. Min Act: -0.1700
Data Index: 5330009 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3204. Min Act: -0.1700
Data Index: 1754326 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3047. Min Act: -0.1700
Data Index: 3998612 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.2890. Min Act: -0.1700
Data Index: 7151789 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3047. Min Act: -0.1700
Data Index: 5274003 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3047. Min Act: -0.1700
Data Index: 8625632 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.2890. Min Act: -0.1700
Data Index: 3758480 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.2733. Min Act: -0.1700
Data Index: 7990044 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.3047. Min Act: -0.1700
Data Index: 7999456 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7433. Min Range: -3.7433
Max Act: 3.2890. Min Act: -0.1700
Data Index: 4789510 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19