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

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

Neuron 5043 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: 3.7213. Min Range: -3.7213

Max Act: 3.7213. Min Act: -0.0000

Data Index: 574352 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 3.7213. Min Range: -3.7213

Max Act: 3.3705. Min Act: -0.0000

Data Index: 1276277 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 3.7213. Min Range: -3.7213

Max Act: 3.0355. Min Act: -0.0000

Data Index: 388993 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.9409. Min Act: -0.0000

Data Index: 51538 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.8667. Min Act: -0.0000

Data Index: 127848 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.5510. Min Act: -0.0000

Data Index: 708398 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 3.7213. Min Range: -3.7213

Max Act: 3.0581. Min Act: -0.0000

Data Index: 809155 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.7688. Min Act: -0.0000

Data Index: 865776 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.7137. Min Act: -0.0000

Data Index: 1162202 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.7164. Min Act: -0.0000

Data Index: 511 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.2487. Min Act: -0.0000

Data Index: 1078274 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.4190. Min Act: -0.0000

Data Index: 323474 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.4003. Min Act: -0.0000

Data Index: 201570 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.3811. Min Act: -0.0000

Data Index: 926575 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.3595. Min Act: -0.0000

Data Index: 455667 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.3676. Min Act: -0.0000

Data Index: 42932 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.3183. Min Act: -0.0000

Data Index: 882172 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.1752. Min Act: -0.0000

Data Index: 1164951 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.1719. Min Act: 0.0000

Data Index: 206871 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 3.7213. Min Range: -3.7213

Max Act: 2.1247. Min Act: -0.0000

Data Index: 943369 (C4 (Web Text))

Max Activating Token Index: 650