Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5829 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.8319. Min Act: -0.1700
Data Index: 5914779 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.8319. Min Act: -0.1700
Data Index: 2195295 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.8007. Min Act: -0.1700
Data Index: 644924 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7694. Min Act: -0.1700
Data Index: 8119717 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7381. Min Act: -0.1700
Data Index: 5836982 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7381. Min Act: -0.1700
Data Index: 5200878 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7694. Min Act: -0.1700
Data Index: 6013386 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7381. Min Act: -0.1700
Data Index: 921452 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7381. Min Act: -0.1700
Data Index: 6268538 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7381. Min Act: -0.1700
Data Index: 829201 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.7068. Min Act: -0.1700
Data Index: 575028 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6755. Min Act: -0.1700
Data Index: 1596245 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6442. Min Act: -0.1700
Data Index: 1515067 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6442. Min Act: -0.1700
Data Index: 3434241 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6442. Min Act: -0.1700
Data Index: 1377857 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6129. Min Act: -0.1700
Data Index: 6280651 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6129. Min Act: -0.1700
Data Index: 2142619 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6129. Min Act: -0.1700
Data Index: 3854795 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6442. Min Act: -0.1700
Data Index: 5868508 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8319. Min Range: -3.8319
Max Act: 3.6129. Min Act: -0.1700
Data Index: 198464 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19