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

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

Neuron 160 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3148. Min Range: -4.3148

Max Act: 4.2699. Min Act: -0.0000

Data Index: 1238703 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 4.3148. Min Range: -4.3148

Max Act: 4.3148. Min Act: -0.0000

Data Index: 1560479 (Python Code)

Max Activating Token Index: 324

Text #2

Max Range: 4.3148. Min Range: -4.3148

Max Act: 4.1156. Min Act: -0.0000

Data Index: 1405440 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 4.3148. Min Range: -4.3148

Max Act: 3.5800. Min Act: -0.0000

Data Index: 479913 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 4.3148. Min Range: -4.3148

Max Act: 3.3752. Min Act: -0.0000

Data Index: 846501 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 4.3148. Min Range: -4.3148

Max Act: 3.2521. Min Act: -0.0000

Data Index: 655645 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 4.3148. Min Range: -4.3148

Max Act: 3.1810. Min Act: -0.0000

Data Index: 1179112 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.9118. Min Act: -0.0000

Data Index: 299654 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 4.3148. Min Range: -4.3148

Max Act: 3.5933. Min Act: -0.0000

Data Index: 451905 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 4.3148. Min Range: -4.3148

Max Act: 3.1574. Min Act: -0.0000

Data Index: 747899 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.9785. Min Act: -0.0000

Data Index: 789912 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.7682. Min Act: -0.0000

Data Index: 353873 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.5600. Min Act: -0.0000

Data Index: 1226349 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.6692. Min Act: -0.0000

Data Index: 828431 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.7570. Min Act: -0.0000

Data Index: 752231 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.9079. Min Act: -0.0000

Data Index: 1357972 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.5470. Min Act: -0.0000

Data Index: 989960 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.4951. Min Act: -0.0000

Data Index: 984517 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.6830. Min Act: -0.0000

Data Index: 1452228 (Python Code)

Max Activating Token Index: 948

Text #19

Max Range: 4.3148. Min Range: -4.3148

Max Act: 2.6792. Min Act: -0.0000

Data Index: 370984 (C4 (Web Text))

Max Activating Token Index: 187