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

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

Neuron 5428 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.3227. Min Act: -0.0001

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.8564. Min Act: -0.0001

Data Index: 423123 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.9474. Min Act: -0.0001

Data Index: 877758 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.7855. Min Act: -0.0001

Data Index: 819103 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.6603. Min Act: -0.0001

Data Index: 889710 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.0529. Min Act: -0.0001

Data Index: 312275 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 3.3227. Min Range: -3.3227

Max Act: 3.0621. Min Act: -0.0001

Data Index: 296352 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.4200. Min Act: -0.0001

Data Index: 31394 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.5669. Min Act: -0.0001

Data Index: 1222150 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.4990. Min Act: -0.0000

Data Index: 210557 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.2154. Min Act: -0.0001

Data Index: 694890 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.3197. Min Act: -0.0001

Data Index: 48198 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 3.3227. Min Range: -3.3227

Max Act: 1.9178. Min Act: -0.0001

Data Index: 36683 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.2531. Min Act: -0.0001

Data Index: 1064192 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 3.3227. Min Range: -3.3227

Max Act: 1.9234. Min Act: -0.0001

Data Index: 593904 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.1202. Min Act: -0.0001

Data Index: 1331471 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 3.3227. Min Range: -3.3227

Max Act: 1.9982. Min Act: -0.0001

Data Index: 666322 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.0934. Min Act: -0.0001

Data Index: 737184 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 3.3227. Min Range: -3.3227

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1167103 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 3.3227. Min Range: -3.3227

Max Act: 2.0391. Min Act: -0.0001

Data Index: 673366 (C4 (Web Text))

Max Activating Token Index: 1020