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

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

Neuron 575 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: 3.8359. Min Range: -3.8359

Max Act: 3.8359. Min Act: -0.0000

Data Index: 688736 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.7801. Min Act: -0.0000

Data Index: 1204627 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.6525. Min Act: -0.0000

Data Index: 1028874 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.6459. Min Act: -0.0000

Data Index: 1039392 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3927. Min Act: -0.0000

Data Index: 643899 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3298. Min Act: -0.0000

Data Index: 1244162 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1614. Min Act: -0.0000

Data Index: 68363 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1177. Min Act: -0.0000

Data Index: 524875 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.2515. Min Act: -0.0000

Data Index: 232544 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.2594. Min Act: -0.0000

Data Index: 575165 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.2019. Min Act: -0.0000

Data Index: 250373 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1560. Min Act: -0.0000

Data Index: 1155235 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.2823. Min Act: -0.0000

Data Index: 147990 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1236. Min Act: -0.0000

Data Index: 1110972 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.0504. Min Act: -0.0000

Data Index: 1033072 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.0440. Min Act: -0.0000

Data Index: 343407 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 3.8359. Min Range: -3.8359

Max Act: 2.9000. Min Act: -0.0000

Data Index: 1127771 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1922. Min Act: -0.0000

Data Index: 1225282 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.1405. Min Act: -0.0000

Data Index: 943043 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 3.8359. Min Range: -3.8359

Max Act: 2.9341. Min Act: -0.0000

Data Index: 1279438 (C4 (Web Text))

Max Activating Token Index: 512