Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3859 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1131. Min Range: -8.1131
Max Act: 8.1131. Min Act: -0.1700
Data Index: 1398175 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.8943. Min Act: -0.1700
Data Index: 783803 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.6756. Min Act: -0.1700
Data Index: 7310491 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.6131. Min Act: -0.1700
Data Index: 5737532 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.5193. Min Act: -0.1700
Data Index: 7165944 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.4881. Min Act: -0.1700
Data Index: 6217143 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.4881. Min Act: -0.1700
Data Index: 1051389 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.4256. Min Act: -0.1700
Data Index: 8539787 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.4256. Min Act: -0.1700
Data Index: 8433821 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3943. Min Act: -0.1700
Data Index: 1580443 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3943. Min Act: -0.1700
Data Index: 6583383 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3943. Min Act: -0.1700
Data Index: 581940 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3631. Min Act: -0.1700
Data Index: 2071909 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3631. Min Act: -0.1700
Data Index: 5687435 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3631. Min Act: -0.1700
Data Index: 6680691 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3006. Min Act: -0.1700
Data Index: 7298478 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3006. Min Act: -0.1700
Data Index: 4138103 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.2693. Min Act: -0.1700
Data Index: 3801424 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.2693. Min Act: -0.1700
Data Index: 3906515 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1131. Min Range: -8.1131
Max Act: 7.3006. Min Act: -0.1700
Data Index: 2917930 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19