Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3782 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.6272. Min Act: -0.0000

Data Index: 87946 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5329. Min Act: -0.0001

Data Index: 552506 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5516. Min Act: 0.0001

Data Index: 1372668 (Python Code)

Max Activating Token Index: 142

Text #4

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5283. Min Act: -0.0001

Data Index: 488458 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5680. Min Act: -0.0001

Data Index: 1112246 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5430. Min Act: -0.0000

Data Index: 630473 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5232. Min Act: -0.0000

Data Index: 405257 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5212. Min Act: -0.0001

Data Index: 252507 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5203. Min Act: 0.0000

Data Index: 1367350 (Python Code)

Max Activating Token Index: 721

Text #10

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5500. Min Act: -0.0001

Data Index: 495360 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5267. Min Act: -0.0001

Data Index: 607877 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5247. Min Act: -0.0001

Data Index: 655181 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5205. Min Act: -0.0000

Data Index: 29090 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5034. Min Act: -0.0000

Data Index: 296620 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1279659 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5097. Min Act: -0.0000

Data Index: 113279 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1035240 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.4666. Min Act: -0.0001

Data Index: 1325110 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.6711. Min Range: -0.6711

Max Act: 0.5874. Min Act: -0.0001

Data Index: 911142 (C4 (Web Text))

Max Activating Token Index: 756