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

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

Neuron 3907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0467. Min Range: -1.0467

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1354840 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 1.0467. Min Range: -1.0467

Max Act: 1.0467. Min Act: -0.0000

Data Index: 484635 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.0467. Min Range: -1.0467

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1056156 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9925. Min Act: -0.0000

Data Index: 186609 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9817. Min Act: -0.0000

Data Index: 409568 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8884. Min Act: -0.0000

Data Index: 447539 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.9130. Min Act: -0.0000

Data Index: 50652 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8975. Min Act: -0.0000

Data Index: 714456 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8337. Min Act: -0.0000

Data Index: 313022 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8456. Min Act: -0.0000

Data Index: 441975 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8485. Min Act: -0.0000

Data Index: 772150 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8357. Min Act: -0.0000

Data Index: 472642 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8204. Min Act: -0.0000

Data Index: 285915 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8020. Min Act: -0.0000

Data Index: 85659 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8014. Min Act: -0.0000

Data Index: 760158 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.7854. Min Act: -0.0000

Data Index: 305989 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1259108 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1277721 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.8260. Min Act: -0.0000

Data Index: 403505 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 1.0467. Min Range: -1.0467

Max Act: 0.7775. Min Act: -0.0000

Data Index: 325169 (C4 (Web Text))

Max Activating Token Index: 168