Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3887. Min Range: -5.3887
Max Act: 5.3887. Min Act: -0.1700
Data Index: 1953630 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3887. Min Range: -5.3887
Max Act: 5.2324. Min Act: -0.1700
Data Index: 8442883 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3887. Min Range: -5.3887
Max Act: 5.0137. Min Act: -0.1700
Data Index: 385411 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.9824. Min Act: -0.1700
Data Index: 7595655 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.8887. Min Act: -0.1700
Data Index: 7331559 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.8887. Min Act: -0.1700
Data Index: 7083554 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.8262. Min Act: -0.1700
Data Index: 2395307 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.8262. Min Act: -0.1700
Data Index: 67121 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7637. Min Act: -0.1700
Data Index: 3742721 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.8262. Min Act: -0.1700
Data Index: 1918163 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7949. Min Act: -0.1700
Data Index: 7403739 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.8262. Min Act: -0.1700
Data Index: 5609560 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7637. Min Act: -0.1700
Data Index: 4474299 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7637. Min Act: -0.1700
Data Index: 8770376 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7637. Min Act: -0.1700
Data Index: 2099910 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7637. Min Act: -0.1700
Data Index: 1950018 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7324. Min Act: -0.1700
Data Index: 2114466 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7324. Min Act: -0.1700
Data Index: 839611 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7324. Min Act: -0.1700
Data Index: 5405583 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3887. Min Range: -5.3887
Max Act: 4.7324. Min Act: -0.1700
Data Index: 5581809 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19