Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.1218. Min Act: -0.1700
Data Index: 2834100 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.1531. Min Act: -0.1700
Data Index: 8156915 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1531. Min Range: -5.1531
Max Act: 5.0906. Min Act: -0.1700
Data Index: 2523935 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9656. Min Act: -0.1700
Data Index: 4965755 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9343. Min Act: -0.1700
Data Index: 3304441 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.8718. Min Act: -0.1700
Data Index: 2242095 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.9031. Min Act: -0.1700
Data Index: 446231 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.8718. Min Act: -0.1700
Data Index: 1102439 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.8406. Min Act: -0.1700
Data Index: 3467729 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7781. Min Act: -0.1700
Data Index: 3717979 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7781. Min Act: -0.1700
Data Index: 2794220 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7781. Min Act: -0.1700
Data Index: 7612586 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7468. Min Act: -0.1700
Data Index: 5433727 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7468. Min Act: -0.1700
Data Index: 2347786 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7468. Min Act: -0.1700
Data Index: 5102823 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7468. Min Act: -0.1700
Data Index: 574840 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7468. Min Act: -0.1700
Data Index: 1500143 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7468. Min Act: -0.1700
Data Index: 5701485 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7468. Min Act: -0.1700
Data Index: 1219358 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1531. Min Range: -5.1531
Max Act: 4.7156. Min Act: -0.1700
Data Index: 5294042 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19