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

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

Neuron 3960 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: 1.9751. Min Range: -1.9751

Max Act: 1.9751. Min Act: -0.0000

Data Index: 1164053 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4408. Min Act: -0.0000

Data Index: 948065 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4071. Min Act: -0.0000

Data Index: 209956 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3908. Min Act: -0.0000

Data Index: 672580 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3338. Min Act: -0.0000

Data Index: 910654 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1244700 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.2406. Min Act: -0.0000

Data Index: 20653 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3145. Min Act: -0.0000

Data Index: 17136 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.2213. Min Act: -0.0000

Data Index: 169311 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.2022. Min Act: -0.0000

Data Index: 1245782 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.1509. Min Act: -0.0000

Data Index: 819587 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1156508 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1067645 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.2321. Min Act: -0.0000

Data Index: 952390 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1341337 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.0678. Min Act: -0.0000

Data Index: 1270849 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.1301. Min Act: -0.0000

Data Index: 955978 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.1556. Min Act: -0.0000

Data Index: 299076 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.1020. Min Act: -0.0000

Data Index: 995057 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.9751. Min Range: -1.9751

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1583260 (Python Code)

Max Activating Token Index: 197