Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1699. Min Range: -5.1699
Max Act: 5.1699. Min Act: -0.1700
Data Index: 569619 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.9824. Min Act: -0.1700
Data Index: 1431832 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7949. Min Act: -0.1700
Data Index: 8101015 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7636. Min Act: -0.1700
Data Index: 3095827 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7636. Min Act: -0.1700
Data Index: 2289039 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7324. Min Act: -0.1700
Data Index: 2977659 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7636. Min Act: -0.1700
Data Index: 7645871 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7324. Min Act: -0.1700
Data Index: 6267453 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7011. Min Act: -0.1700
Data Index: 3812677 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7011. Min Act: -0.1700
Data Index: 1366985 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7011. Min Act: -0.1700
Data Index: 1850523 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.7011. Min Act: -0.1700
Data Index: 8393638 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6699. Min Act: -0.1700
Data Index: 4899 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6699. Min Act: -0.1700
Data Index: 5965126 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6699. Min Act: -0.1700
Data Index: 7484527 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6386. Min Act: -0.1700
Data Index: 6136050 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6386. Min Act: -0.1700
Data Index: 6983344 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6386. Min Act: -0.1700
Data Index: 2448980 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6386. Min Act: -0.1700
Data Index: 6388682 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1699. Min Range: -5.1699
Max Act: 4.6386. Min Act: -0.1700
Data Index: 6728623 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19