Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1200. Min Range: -4.1200
Max Act: 4.1200. Min Act: -0.1659
Data Index: 7389492 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1200. Min Range: -4.1200
Max Act: 4.1200. Min Act: -0.1661
Data Index: 8186322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1200. Min Range: -4.1200
Max Act: 4.0262. Min Act: -0.1696
Data Index: 7389491 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.9637. Min Act: -0.1700
Data Index: 8186323 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.9950. Min Act: -0.1700
Data Index: 8186324 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.9324. Min Act: -0.1699
Data Index: 7389490 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.9012. Min Act: -0.1699
Data Index: 7389493 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.6510. Min Act: -0.1699
Data Index: 8186321 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.3690. Min Act: -0.1639
Data Index: 7913474 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.3063. Min Act: -0.1700
Data Index: 8470124 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.2749. Min Act: -0.1699
Data Index: 1402286 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.2434. Min Act: -0.1639
Data Index: 7913475 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.2434. Min Act: -0.1700
Data Index: 42922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.1491. Min Act: -0.1699
Data Index: 8815990 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.0230. Min Act: -0.1700
Data Index: 3736015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1200. Min Range: -4.1200
Max Act: 3.0230. Min Act: -0.1700
Data Index: 42923 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1200. Min Range: -4.1200
Max Act: 2.9597. Min Act: -0.1686
Data Index: 7913476 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1200. Min Range: -4.1200
Max Act: 2.9280. Min Act: -0.1699
Data Index: 6420381 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1200. Min Range: -4.1200
Max Act: 2.9280. Min Act: -0.1700
Data Index: 6262487 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1200. Min Range: -4.1200
Max Act: 2.9280. Min Act: -0.1700
Data Index: 1402285 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19