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

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

Neuron 3520 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: 1.6344. Min Range: -1.6344

Max Act: 1.6270. Min Act: -0.0000

Data Index: 493143 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.6344. Min Act: -0.0000

Data Index: 493761 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.1940. Min Act: -0.0000

Data Index: 1133970 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.0465. Min Act: -0.0000

Data Index: 966003 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.9636. Min Act: -0.0000

Data Index: 186626 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1215832 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.9061. Min Act: -0.0000

Data Index: 248767 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 1.6344. Min Range: -1.6344

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1245671 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.9030. Min Act: -0.0000

Data Index: 800858 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.8961. Min Act: -0.0000

Data Index: 213749 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.9929. Min Act: -0.0000

Data Index: 390243 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.9300. Min Act: -0.0000

Data Index: 232022 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.8980. Min Act: -0.0000

Data Index: 927553 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.8808. Min Act: -0.0000

Data Index: 685087 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.9094. Min Act: -0.0000

Data Index: 601058 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.8428. Min Act: -0.0000

Data Index: 655821 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.8341. Min Act: -0.0000

Data Index: 925050 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.7599. Min Act: -0.0000

Data Index: 940779 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.8539. Min Act: -0.0000

Data Index: 461966 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.6344. Min Range: -1.6344

Max Act: 0.7919. Min Act: -0.0000

Data Index: 195866 (C4 (Web Text))

Max Activating Token Index: 715