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

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

Neuron 5438 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4988. Min Act: -0.0000

Data Index: 149652 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.5047. Min Act: -0.0000

Data Index: 900202 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1335416 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4675. Min Act: -0.0000

Data Index: 8826 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4772. Min Act: -0.0000

Data Index: 706443 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4696. Min Act: -0.0000

Data Index: 858240 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4466. Min Act: -0.0000

Data Index: 497675 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1043925 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4592. Min Act: -0.0000

Data Index: 10910 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4344. Min Act: -0.0000

Data Index: 721925 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1248786 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4487. Min Act: -0.0000

Data Index: 942359 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4454. Min Act: -0.0000

Data Index: 234890 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4403. Min Act: -0.0000

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4209. Min Act: -0.0000

Data Index: 923355 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4315. Min Act: -0.0000

Data Index: 736758 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4349. Min Act: -0.0000

Data Index: 715638 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4180. Min Act: -0.0000

Data Index: 667153 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.4272. Min Act: -0.0000

Data Index: 288643 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.5047. Min Range: -0.5047

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1020242 (C4 (Web Text))

Max Activating Token Index: 970