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

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

Neuron 5701 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6346. Min Act: -0.0000

Data Index: 595687 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.6001. Min Act: -0.0000

Data Index: 103609 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5708. Min Act: -0.0000

Data Index: 495232 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1007681 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5538. Min Act: -0.0000

Data Index: 256548 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1512401 (Python Code)

Max Activating Token Index: 757

Text #6

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5837. Min Act: -0.0000

Data Index: 70053 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5283. Min Act: -0.0000

Data Index: 485716 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5006. Min Act: -0.0000

Data Index: 647796 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5191. Min Act: -0.0000

Data Index: 566670 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1289107 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5325. Min Act: -0.0000

Data Index: 1444911 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5148. Min Act: 0.0001

Data Index: 724289 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1234967 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5736. Min Act: -0.0000

Data Index: 158700 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4698. Min Act: -0.0000

Data Index: 906144 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1063251 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1330344 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4777. Min Act: -0.0000

Data Index: 820020 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.6346. Min Range: -0.6346

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1539483 (Python Code)

Max Activating Token Index: 650