Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1051 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.7781. Min Act: -0.0000

Data Index: 924934 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.6252. Min Act: -0.0000

Data Index: 268988 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1089031 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5376. Min Act: -0.0001

Data Index: 1319985 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5355. Min Act: -0.0000

Data Index: 120250 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1164278 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5118. Min Act: -0.0000

Data Index: 151786 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5603. Min Act: -0.0000

Data Index: 642696 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1242631 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5399. Min Act: -0.0000

Data Index: 154949 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5379. Min Act: -0.0000

Data Index: 855659 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4969. Min Act: -0.0000

Data Index: 883824 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5041. Min Act: -0.0000

Data Index: 571529 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4874. Min Act: -0.0000

Data Index: 972618 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5215. Min Act: -0.0000

Data Index: 423733 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4796. Min Act: -0.0000

Data Index: 814745 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4910. Min Act: -0.0000

Data Index: 85542 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.4849. Min Act: -0.0000

Data Index: 409985 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5056. Min Act: -0.0000

Data Index: 273087 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.7781. Min Range: -0.7781

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1025924 (C4 (Web Text))

Max Activating Token Index: 183