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

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

Neuron 4079 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6440. Min Range: -2.6440

Max Act: 2.5289. Min Act: -0.0000

Data Index: 938311 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 2.6440. Min Range: -2.6440

Max Act: 2.6440. Min Act: -0.0000

Data Index: 282971 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 2.6440. Min Range: -2.6440

Max Act: 2.5172. Min Act: -0.0000

Data Index: 721923 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 2.6440. Min Range: -2.6440

Max Act: 2.4773. Min Act: -0.0000

Data Index: 934341 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 2.6440. Min Range: -2.6440

Max Act: 2.4718. Min Act: -0.0000

Data Index: 431239 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 2.6440. Min Range: -2.6440

Max Act: 2.2433. Min Act: -0.0000

Data Index: 968356 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.8181. Min Act: -0.0000

Data Index: 732139 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.8805. Min Act: -0.0000

Data Index: 200954 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.8336. Min Act: -0.0000

Data Index: 790372 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.8214. Min Act: -0.0000

Data Index: 1614642 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.7091. Min Act: -0.0000

Data Index: 1023632 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.6553. Min Act: -0.0000

Data Index: 995867 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.6349. Min Act: -0.0000

Data Index: 1237749 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.7162. Min Act: -0.0000

Data Index: 1237165 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.5511. Min Act: -0.0000

Data Index: 469938 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.5171. Min Act: -0.0000

Data Index: 188245 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1627732 (Python Code)

Max Activating Token Index: 306

Text #17

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.6077. Min Act: -0.0000

Data Index: 133884 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.5245. Min Act: -0.0000

Data Index: 390295 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 2.6440. Min Range: -2.6440

Max Act: 1.5836. Min Act: -0.0000

Data Index: 817865 (C4 (Web Text))

Max Activating Token Index: 211