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

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

Neuron 5312 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: 1.2411. Min Range: -1.2411

Max Act: 1.2411. Min Act: -0.0001

Data Index: 220305 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.2411. Min Range: -1.2411

Max Act: 1.1810. Min Act: -0.0001

Data Index: 1001365 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 1.2411. Min Range: -1.2411

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1090858 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.2411. Min Range: -1.2411

Max Act: 1.0479. Min Act: -0.0001

Data Index: 79217 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.2411. Min Range: -1.2411

Max Act: 1.0177. Min Act: -0.0001

Data Index: 205968 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 1.2411. Min Range: -1.2411

Max Act: 1.0006. Min Act: -0.0001

Data Index: 962094 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8812. Min Act: -0.0000

Data Index: 87482 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.9304. Min Act: -0.0000

Data Index: 166546 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1352010 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.9420. Min Act: -0.0000

Data Index: 835794 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.9063. Min Act: -0.0000

Data Index: 1153807 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.9256. Min Act: -0.0000

Data Index: 456508 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1106587 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8671. Min Act: -0.0001

Data Index: 195030 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8423. Min Act: -0.0001

Data Index: 136051 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8584. Min Act: -0.0001

Data Index: 409634 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8527. Min Act: -0.0000

Data Index: 488624 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.9145. Min Act: -0.0001

Data Index: 41878 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8444. Min Act: -0.0001

Data Index: 1107460 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 1.2411. Min Range: -1.2411

Max Act: 0.8052. Min Act: -0.0001

Data Index: 1350548 (C4 (Web Text))

Max Activating Token Index: 49