Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3701 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.5394. Min Act: -0.0001

Data Index: 869730 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4769. Min Act: -0.0001

Data Index: 241482 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4681. Min Act: -0.0001

Data Index: 219336 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4812. Min Act: -0.0001

Data Index: 160602 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4757. Min Act: -0.0001

Data Index: 950178 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4926. Min Act: -0.0001

Data Index: 1253567 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4231. Min Act: -0.0001

Data Index: 1306539 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1189989 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3883. Min Act: -0.0001

Data Index: 255944 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1231719 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4308. Min Act: -0.0001

Data Index: 802909 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4011. Min Act: -0.0001

Data Index: 822987 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4208. Min Act: -0.0001

Data Index: 890229 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4210. Min Act: -0.0001

Data Index: 288887 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3927. Min Act: -0.0001

Data Index: 1337224 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4038. Min Act: -0.0001

Data Index: 111122 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1004864 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4020. Min Act: -0.0001

Data Index: 760643 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4619. Min Act: -0.0001

Data Index: 746805 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.5394. Min Range: -0.5394

Max Act: 0.4012. Min Act: -0.0001

Data Index: 635488 (C4 (Web Text))

Max Activating Token Index: 991