Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3638. Min Range: -7.3638
Max Act: 7.3638. Min Act: -0.1700
Data Index: 16474 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3638. Min Range: -7.3638
Max Act: 7.1138. Min Act: -0.1700
Data Index: 6559871 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.9575. Min Act: -0.1700
Data Index: 7849390 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.9263. Min Act: -0.1700
Data Index: 5060360 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.8013. Min Act: -0.1700
Data Index: 3447082 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.7075. Min Act: -0.1700
Data Index: 1150562 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.6450. Min Act: -0.1700
Data Index: 2454668 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.6450. Min Act: -0.1700
Data Index: 8821776 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.6138. Min Act: -0.1700
Data Index: 5586253 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.5513. Min Act: -0.1700
Data Index: 6421764 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.5200. Min Act: -0.1700
Data Index: 557902 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.5513. Min Act: -0.1700
Data Index: 8549410 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 284364 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 8270456 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 8471803 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.4888. Min Act: -0.1700
Data Index: 6207524 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.4575. Min Act: -0.1700
Data Index: 5016338 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.4263. Min Act: -0.1700
Data Index: 8283133 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.3950. Min Act: -0.1700
Data Index: 6332032 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3638. Min Range: -7.3638
Max Act: 6.4263. Min Act: -0.1700
Data Index: 3481066 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19