Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5028 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5933. Min Act: -0.0000

Data Index: 150317 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.7318. Min Act: -0.0000

Data Index: 1201637 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.6964. Min Act: -0.0000

Data Index: 792232 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5673. Min Act: -0.0000

Data Index: 106488 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5193. Min Act: -0.0000

Data Index: 820419 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5257. Min Act: -0.0000

Data Index: 1188372 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.6153. Min Act: -0.0000

Data Index: 1292915 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5923. Min Act: -0.0000

Data Index: 1024850 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5529. Min Act: -0.0000

Data Index: 655417 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5297. Min Act: -0.0000

Data Index: 1087296 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5403. Min Act: -0.0000

Data Index: 1283889 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5300. Min Act: -0.0000

Data Index: 176121 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.6506. Min Act: -0.0000

Data Index: 331106 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.5282. Min Act: -0.0000

Data Index: 6899 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.6361. Min Act: -0.0000

Data Index: 235701 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.4879. Min Act: -0.0000

Data Index: 415669 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.4871. Min Act: -0.0000

Data Index: 316843 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.4646. Min Act: -0.0000

Data Index: 1169372 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.3389. Min Act: -0.0000

Data Index: 1341929 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 2.7318. Min Range: -2.7318

Max Act: 2.4813. Min Act: -0.0000

Data Index: 214827 (C4 (Web Text))

Max Activating Token Index: 551