Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4877 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.9608. Min Act: -0.1700
Data Index: 5963343 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.8358. Min Act: -0.1700
Data Index: 7813779 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.7733. Min Act: -0.1700
Data Index: 7440972 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.7420. Min Act: -0.1700
Data Index: 3650149 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.6483. Min Act: -0.1700
Data Index: 3538579 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.5858. Min Act: -0.1700
Data Index: 5566525 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.5233. Min Act: -0.1700
Data Index: 7771322 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.4608. Min Act: -0.1700
Data Index: 2179781 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.3670. Min Act: -0.1700
Data Index: 5300825 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.3983. Min Act: -0.1700
Data Index: 8423259 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.3358. Min Act: -0.1700
Data Index: 3473707 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.3358. Min Act: -0.1700
Data Index: 1818502 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.2733. Min Act: -0.1700
Data Index: 844742 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.2420. Min Act: -0.1700
Data Index: 1114456 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.2420. Min Act: -0.1700
Data Index: 6163789 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.2108. Min Act: -0.1700
Data Index: 4420624 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.1795. Min Act: -0.1700
Data Index: 3473691 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.1795. Min Act: -0.1700
Data Index: 8028598 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.1795. Min Act: -0.1700
Data Index: 7940270 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9608. Min Range: -7.9608
Max Act: 7.1483. Min Act: -0.1700
Data Index: 5051833 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19