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

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

Neuron 5462 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: 0.5635. Min Range: -0.5635

Max Act: 0.5635. Min Act: -0.0000

Data Index: 287687 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1156330 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1135602 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.5174. Min Act: -0.0000

Data Index: 460095 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4740. Min Act: -0.0000

Data Index: 604702 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4779. Min Act: -0.0001

Data Index: 467500 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4729. Min Act: -0.0000

Data Index: 96853 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4743. Min Act: -0.0000

Data Index: 572297 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4559. Min Act: -0.0000

Data Index: 23960 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4687. Min Act: -0.0000

Data Index: 171800 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4624. Min Act: -0.0000

Data Index: 463159 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4243. Min Act: -0.0000

Data Index: 29820 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4335. Min Act: -0.0000

Data Index: 325109 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4160. Min Act: -0.0000

Data Index: 592805 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4578. Min Act: -0.0000

Data Index: 191616 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4215. Min Act: -0.0000

Data Index: 974412 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4205. Min Act: -0.0000

Data Index: 318240 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4294. Min Act: -0.0000

Data Index: 1068691 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1007048 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.5635. Min Range: -0.5635

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1093604 (C4 (Web Text))

Max Activating Token Index: 412