Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3424 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5340. Min Act: -0.0001

Data Index: 352812 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5795. Min Act: -0.0002

Data Index: 120895 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5703. Min Act: -0.0001

Data Index: 1015965 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5140. Min Act: -0.0002

Data Index: 374308 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5552. Min Act: -0.0002

Data Index: 595283 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.4286. Min Act: -0.0001

Data Index: 864292 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5144. Min Act: -0.0001

Data Index: 1317937 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.5014. Min Act: -0.0001

Data Index: 844943 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.4539. Min Act: -0.0001

Data Index: 196821 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.3781. Min Act: -0.0001

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.4079. Min Act: -0.0002

Data Index: 126522 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.3482. Min Act: -0.0002

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.3502. Min Act: -0.0002

Data Index: 759984 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.3473. Min Act: -0.0002

Data Index: 1147910 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.4537. Min Act: -0.0001

Data Index: 1049203 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.3065. Min Act: -0.0002

Data Index: 86760 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.4164. Min Act: -0.0002

Data Index: 1114646 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.3208. Min Act: -0.0002

Data Index: 966585 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.2548. Min Act: -0.0002

Data Index: 672196 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 1.5795. Min Range: -1.5795

Max Act: 1.2323. Min Act: -0.0001

Data Index: 1090553 (C4 (Web Text))

Max Activating Token Index: 328