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

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

Neuron 2379 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.2586. Min Act: -0.0001

Data Index: 816422 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.1048. Min Act: -0.0001

Data Index: 266863 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.1280. Min Act: -0.0002

Data Index: 591056 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9639. Min Act: -0.0002

Data Index: 259426 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.1608. Min Act: -0.0001

Data Index: 698054 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.2586. Min Range: -1.2586

Max Act: 1.0708. Min Act: -0.0002

Data Index: 707624 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9541. Min Act: -0.0001

Data Index: 1415432 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9436. Min Act: -0.0001

Data Index: 1439854 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1632124 (Python Code)

Max Activating Token Index: 938

Text #9

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9371. Min Act: -0.0001

Data Index: 1090675 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8732. Min Act: -0.0002

Data Index: 1054516 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8877. Min Act: -0.0001

Data Index: 1496128 (Python Code)

Max Activating Token Index: 19

Text #12

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9220. Min Act: -0.0001

Data Index: 999827 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8818. Min Act: -0.0001

Data Index: 1181401 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9438. Min Act: -0.0001

Data Index: 1606481 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.9083. Min Act: -0.0001

Data Index: 222887 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8701. Min Act: -0.0002

Data Index: 651600 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8674. Min Act: -0.0002

Data Index: 1084741 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8205. Min Act: -0.0002

Data Index: 338839 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 1.2586. Min Range: -1.2586

Max Act: 0.8769. Min Act: -0.0002

Data Index: 834177 (C4 (Web Text))

Max Activating Token Index: 448