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

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

Neuron 3058 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0176. Min Range: -1.0176

Max Act: 1.0176. Min Act: -0.0000

Data Index: 320836 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.9938. Min Act: -0.0000

Data Index: 805144 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.9179. Min Act: -0.0000

Data Index: 850280 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8667. Min Act: -0.0000

Data Index: 783199 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1332208 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1061684 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1094421 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1295702 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8408. Min Act: -0.0000

Data Index: 422759 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8602. Min Act: -0.0000

Data Index: 812300 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8515. Min Act: -0.0000

Data Index: 167635 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8777. Min Act: -0.0000

Data Index: 371957 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8966. Min Act: -0.0001

Data Index: 1005358 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8436. Min Act: -0.0000

Data Index: 125897 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8190. Min Act: -0.0000

Data Index: 921742 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1072473 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.7994. Min Act: -0.0000

Data Index: 622242 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.7984. Min Act: -0.0001

Data Index: 1300662 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.7701. Min Act: -0.0001

Data Index: 1175190 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.0176. Min Range: -1.0176

Max Act: 0.8224. Min Act: -0.0001

Data Index: 944807 (C4 (Web Text))

Max Activating Token Index: 829