Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4223 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.1079. Min Act: -0.0000

Data Index: 550161 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.0216. Min Act: -0.0000

Data Index: 968617 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.9207. Min Act: -0.0000

Data Index: 182039 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1170190 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.8036. Min Act: -0.0000

Data Index: 861131 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1173051 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7670. Min Act: -0.0000

Data Index: 785304 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7608. Min Act: -0.0000

Data Index: 503758 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1359645 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7639. Min Act: -0.0000

Data Index: 914734 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7616. Min Act: -0.0000

Data Index: 885976 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1313460 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7676. Min Act: -0.0000

Data Index: 547609 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1117258 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6897. Min Act: -0.0000

Data Index: 708187 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1193876 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7043. Min Act: -0.0000

Data Index: 387915 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7011. Min Act: -0.0000

Data Index: 706742 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6802. Min Act: -0.0000

Data Index: 457080 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7005. Min Act: -0.0000

Data Index: 584417 (C4 (Web Text))

Max Activating Token Index: 526