Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3421 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3396. Min Range: -9.3396
Max Act: 9.3396. Min Act: -0.1700
Data Index: 8291610 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.9646. Min Act: -0.1700
Data Index: 7568197 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.7146. Min Act: -0.1700
Data Index: 201327 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.6521. Min Act: -0.1700
Data Index: 422299 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.6521. Min Act: -0.1700
Data Index: 7979767 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.6521. Min Act: -0.1700
Data Index: 4328653 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.5271. Min Act: -0.1700
Data Index: 825039 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.5271. Min Act: -0.1700
Data Index: 7837981 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.5271. Min Act: -0.1700
Data Index: 7517809 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.4646. Min Act: -0.1700
Data Index: 5306638 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.5271. Min Act: -0.1700
Data Index: 7915157 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.4646. Min Act: -0.1700
Data Index: 7000151 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.4646. Min Act: -0.1700
Data Index: 4887932 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.4021. Min Act: -0.1700
Data Index: 3524228 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.3396. Min Act: -0.1700
Data Index: 1727071 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.4021. Min Act: -0.1700
Data Index: 7441949 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.2458. Min Act: -0.1700
Data Index: 6372456 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.2146. Min Act: -0.1700
Data Index: 3907611 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.2458. Min Act: -0.1700
Data Index: 5913477 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3396. Min Range: -9.3396
Max Act: 8.2458. Min Act: -0.1700
Data Index: 6397010 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19