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

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

Neuron 202 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0177. Min Range: -2.0177

Max Act: 2.0177. Min Act: -0.0000

Data Index: 350413 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.8352. Min Act: -0.0000

Data Index: 271264 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.7355. Min Act: -0.0000

Data Index: 911691 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.5826. Min Act: -0.0000

Data Index: 562452 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.3683. Min Act: -0.0000

Data Index: 416597 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1203569 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.4903. Min Act: -0.0000

Data Index: 239950 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.3874. Min Act: -0.0000

Data Index: 648636 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.3908. Min Act: -0.0000

Data Index: 443335 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.3859. Min Act: -0.0000

Data Index: 724544 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.3664. Min Act: -0.0000

Data Index: 906064 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1284831 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.4304. Min Act: -0.0000

Data Index: 273567 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.3451. Min Act: -0.0000

Data Index: 297921 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.2661. Min Act: -0.0000

Data Index: 21047 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.2622. Min Act: -0.0000

Data Index: 1154915 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1168108 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.2767. Min Act: -0.0000

Data Index: 13210 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.2710. Min Act: -0.0000

Data Index: 134679 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 2.0177. Min Range: -2.0177

Max Act: 1.2392. Min Act: -0.0000

Data Index: 582027 (C4 (Web Text))

Max Activating Token Index: 320