Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.8002. Min Act: -0.1700
Data Index: 6005222 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.7689. Min Act: -0.1700
Data Index: 7837977 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.5812. Min Act: -0.1700
Data Index: 6445383 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.5342. Min Act: -0.1700
Data Index: 1777252 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.4559. Min Act: -0.1700
Data Index: 2690777 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.4246. Min Act: -0.1700
Data Index: 1184346 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.4089. Min Act: -0.1700
Data Index: 4972015 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3932. Min Act: -0.1700
Data Index: 973686 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3619. Min Act: -0.1700
Data Index: 8687407 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3619. Min Act: -0.1700
Data Index: 6492640 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3619. Min Act: -0.1700
Data Index: 7744416 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3462. Min Act: -0.1700
Data Index: 7849174 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3462. Min Act: -0.1700
Data Index: 3734778 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3305. Min Act: -0.1700
Data Index: 5391345 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3305. Min Act: -0.1700
Data Index: 5205579 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3148. Min Act: -0.1700
Data Index: 2926454 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3148. Min Act: -0.1700
Data Index: 5789818 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3305. Min Act: -0.1700
Data Index: 4719228 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3148. Min Act: -0.1700
Data Index: 1379975 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8002. Min Range: -3.8002
Max Act: 3.3305. Min Act: -0.1700
Data Index: 2645952 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19