Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4999 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7056. Min Range: -6.7056
Max Act: 6.7056. Min Act: -0.1700
Data Index: 7451808 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7056. Min Range: -6.7056
Max Act: 6.2056. Min Act: -0.1700
Data Index: 7513589 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7056. Min Range: -6.7056
Max Act: 6.2056. Min Act: -0.1700
Data Index: 5171089 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7056. Min Range: -6.7056
Max Act: 6.2056. Min Act: -0.1700
Data Index: 6538239 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7056. Min Range: -6.7056
Max Act: 6.2056. Min Act: -0.1700
Data Index: 890258 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7056. Min Range: -6.7056
Max Act: 6.0806. Min Act: -0.1700
Data Index: 5227990 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.9869. Min Act: -0.1700
Data Index: 5989159 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.9244. Min Act: -0.1700
Data Index: 2599294 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.9556. Min Act: -0.1700
Data Index: 30711 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.9244. Min Act: -0.1700
Data Index: 3018140 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.9244. Min Act: -0.1700
Data Index: 4441533 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8931. Min Act: -0.1700
Data Index: 1614820 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8619. Min Act: -0.1700
Data Index: 2036450 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8306. Min Act: -0.1700
Data Index: 7720443 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8306. Min Act: -0.1700
Data Index: 5720684 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8306. Min Act: -0.1700
Data Index: 6519838 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8306. Min Act: -0.1700
Data Index: 970934 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8306. Min Act: -0.1700
Data Index: 1504362 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.8306. Min Act: -0.1700
Data Index: 2370073 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7056. Min Range: -6.7056
Max Act: 5.7994. Min Act: -0.1700
Data Index: 1574103 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19