Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.2859. Min Act: -0.1700
Data Index: 2373963 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.2546. Min Act: -0.1700
Data Index: 3795462 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.2234. Min Act: -0.1700
Data Index: 985074 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.1296. Min Act: -0.1700
Data Index: 376359 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.1609. Min Act: -0.1700
Data Index: 8304671 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.1296. Min Act: -0.1700
Data Index: 5115054 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0984. Min Act: -0.1700
Data Index: 2518900 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.1296. Min Act: -0.1700
Data Index: 1970401 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0671. Min Act: -0.1700
Data Index: 7616598 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0359. Min Act: -0.1700
Data Index: 3273672 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0359. Min Act: -0.1700
Data Index: 512872 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0359. Min Act: -0.1700
Data Index: 1368452 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2859. Min Range: -4.2859
Max Act: 4.0046. Min Act: -0.1700
Data Index: 806277 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9733. Min Act: -0.1700
Data Index: 1247335 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9733. Min Act: -0.1700
Data Index: 1922232 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9733. Min Act: -0.1700
Data Index: 735539 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9733. Min Act: -0.1700
Data Index: 1903674 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9733. Min Act: -0.1700
Data Index: 7348635 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9421. Min Act: -0.1700
Data Index: 6897958 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2859. Min Range: -4.2859
Max Act: 3.9421. Min Act: -0.1700
Data Index: 3745997 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19