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

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

Neuron 1261 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0045. Min Range: -1.0045

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1052901 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.9127. Min Act: -0.0001

Data Index: 326581 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8533. Min Act: -0.0000

Data Index: 79287 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8727. Min Act: -0.0001

Data Index: 1043897 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8353. Min Act: -0.0000

Data Index: 934083 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1124083 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1210048 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7995. Min Act: -0.0001

Data Index: 364985 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8707. Min Act: -0.0000

Data Index: 267332 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.8133. Min Act: -0.0000

Data Index: 647768 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7726. Min Act: -0.0001

Data Index: 562427 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7996. Min Act: -0.0000

Data Index: 598650 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7582. Min Act: -0.0000

Data Index: 337846 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7309. Min Act: -0.0000

Data Index: 73040 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7299. Min Act: -0.0000

Data Index: 289353 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7243. Min Act: -0.0000

Data Index: 545269 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7471. Min Act: -0.0000

Data Index: 615530 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7204. Min Act: -0.0000

Data Index: 676574 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7383. Min Act: -0.0000

Data Index: 538210 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 1.0045. Min Range: -1.0045

Max Act: 0.7133. Min Act: -0.0000

Data Index: 746615 (C4 (Web Text))

Max Activating Token Index: 451