Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1745 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.7628. Min Act: -0.1700
Data Index: 7822070 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.6065. Min Act: -0.1700
Data Index: 5910550 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.5753. Min Act: -0.1700
Data Index: 239679 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.5440. Min Act: -0.1700
Data Index: 2902136 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.5440. Min Act: -0.1700
Data Index: 2330632 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.5128. Min Act: -0.1700
Data Index: 4339938 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.5128. Min Act: -0.1700
Data Index: 6334613 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.5128. Min Act: -0.1700
Data Index: 2359760 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.4815. Min Act: -0.1700
Data Index: 1128267 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.4815. Min Act: -0.1700
Data Index: 1099103 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.4503. Min Act: -0.1700
Data Index: 5145993 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.4190. Min Act: -0.1700
Data Index: 8789121 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.4190. Min Act: -0.1700
Data Index: 8194978 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.4190. Min Act: -0.1700
Data Index: 5215991 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.3878. Min Act: -0.1700
Data Index: 8134750 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.3878. Min Act: -0.1700
Data Index: 5643206 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.3565. Min Act: -0.1700
Data Index: 2448788 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.3565. Min Act: -0.1700
Data Index: 8508271 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.3565. Min Act: -0.1700
Data Index: 7207714 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7628. Min Range: -4.7628
Max Act: 4.3565. Min Act: -0.1700
Data Index: 5719320 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19