Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.4784. Min Act: -0.0000

Data Index: 972715 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.3009. Min Act: -0.0000

Data Index: 960243 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.4619. Min Act: -0.0001

Data Index: 8802 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.3299. Min Act: -0.0000

Data Index: 565068 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1104552 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.3148. Min Act: -0.0000

Data Index: 1090244 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.3609. Min Act: -0.0000

Data Index: 530632 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.3283. Min Act: -0.0000

Data Index: 776318 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.2454. Min Act: -0.0000

Data Index: 730723 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.3043. Min Act: -0.0000

Data Index: 751785 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.3638. Min Act: -0.0001

Data Index: 685852 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.2269. Min Act: -0.0000

Data Index: 21122 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.2426. Min Act: -0.0000

Data Index: 441229 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1086420 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.2360. Min Act: -0.0000

Data Index: 583091 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.2313. Min Act: -0.0000

Data Index: 261370 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.2234. Min Act: -0.0000

Data Index: 156411 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.1432. Min Act: -0.0000

Data Index: 879217 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.2186. Min Act: -0.0000

Data Index: 817549 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.4784. Min Range: -1.4784

Max Act: 1.1929. Min Act: -0.0000

Data Index: 399557 (C4 (Web Text))

Max Activating Token Index: 949