Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3905 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0274. Min Range: -6.0274
Max Act: 6.0274. Min Act: -0.1700
Data Index: 6698454 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.9961. Min Act: -0.1700
Data Index: 7611168 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.9336. Min Act: -0.1700
Data Index: 4942048 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.9336. Min Act: -0.1700
Data Index: 8577778 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.8399. Min Act: -0.1700
Data Index: 2338019 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.8711. Min Act: -0.1700
Data Index: 2362757 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.8399. Min Act: -0.1700
Data Index: 3298973 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.8086. Min Act: -0.1700
Data Index: 1308034 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.7774. Min Act: -0.1700
Data Index: 7326280 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.8086. Min Act: -0.1700
Data Index: 5413401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.7461. Min Act: -0.1700
Data Index: 8344491 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.7149. Min Act: -0.1700
Data Index: 8083284 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.6836. Min Act: -0.1700
Data Index: 5781480 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.6836. Min Act: -0.1700
Data Index: 1713473 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.6211. Min Act: -0.1700
Data Index: 1414431 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.6524. Min Act: -0.1700
Data Index: 4064321 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.6524. Min Act: -0.1700
Data Index: 3311917 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.6524. Min Act: -0.1700
Data Index: 8090229 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.5586. Min Act: -0.1700
Data Index: 2697491 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0274. Min Range: -6.0274
Max Act: 5.5899. Min Act: -0.1700
Data Index: 3980680 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19