Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.5319. Min Act: -0.1700
Data Index: 1181890 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.2507. Min Act: -0.1700
Data Index: 801012 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.1257. Min Act: -0.1700
Data Index: 645604 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.0632. Min Act: -0.1700
Data Index: 6932906 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.0319. Min Act: -0.1700
Data Index: 645606 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.0319. Min Act: -0.1700
Data Index: 6345332 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.0007. Min Act: -0.1700
Data Index: 6110963 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.0007. Min Act: -0.1700
Data Index: 7700485 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5319. Min Range: -6.5319
Max Act: 6.0007. Min Act: -0.1700
Data Index: 4556423 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9694. Min Act: -0.1700
Data Index: 6581268 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 997685 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9382. Min Act: -0.1699
Data Index: 3452638 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 7525771 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 8780283 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 915105 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9382. Min Act: -0.1700
Data Index: 5572984 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9069. Min Act: -0.1700
Data Index: 8671130 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.9069. Min Act: -0.1700
Data Index: 4646859 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.8757. Min Act: -0.1700
Data Index: 6630932 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5319. Min Range: -6.5319
Max Act: 5.8757. Min Act: -0.1700
Data Index: 7233576 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19