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

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

Neuron 198 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.9871. Min Act: -0.0000

Data Index: 487399 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.9663. Min Act: -0.0001

Data Index: 1217528 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.9951. Min Act: -0.0000

Data Index: 367544 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8784. Min Act: -0.0000

Data Index: 189154 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8241. Min Act: -0.0000

Data Index: 196476 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8713. Min Act: -0.0000

Data Index: 169458 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8362. Min Act: -0.0000

Data Index: 946682 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8356. Min Act: -0.0001

Data Index: 644090 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8507. Min Act: -0.0001

Data Index: 673673 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8480. Min Act: -0.0001

Data Index: 951264 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8488. Min Act: -0.0001

Data Index: 393032 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8637. Min Act: -0.0000

Data Index: 637440 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1342702 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8299. Min Act: -0.0001

Data Index: 368517 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8269. Min Act: -0.0000

Data Index: 659358 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8446. Min Act: -0.0001

Data Index: 951067 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1267050 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8090. Min Act: -0.0000

Data Index: 335451 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8056. Min Act: -0.0001

Data Index: 148844 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.9951. Min Range: -0.9951

Max Act: 0.8342. Min Act: -0.0001

Data Index: 788759 (C4 (Web Text))

Max Activating Token Index: 316