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

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

Neuron 2939 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3997. Min Act: -0.0001

Data Index: 78087 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3897. Min Act: -0.0001

Data Index: 387034 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3729. Min Act: -0.0001

Data Index: 1252760 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3624. Min Act: -0.0001

Data Index: 739587 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3599. Min Act: -0.0000

Data Index: 213768 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3406. Min Act: -0.0001

Data Index: 291063 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3445. Min Act: -0.0001

Data Index: 164731 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1644599 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2909. Min Act: -0.0001

Data Index: 781287 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2858. Min Act: -0.0001

Data Index: 547679 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2438. Min Act: -0.0001

Data Index: 824020 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2536. Min Act: -0.0000

Data Index: 139781 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1649180 (Python Code)

Max Activating Token Index: 674

Text #13

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2568. Min Act: -0.0001

Data Index: 55631 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2462. Min Act: -0.0001

Data Index: 542040 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2749. Min Act: -0.0001

Data Index: 372654 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1092323 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2349. Min Act: -0.0001

Data Index: 1597151 (Python Code)

Max Activating Token Index: 687

Text #18

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2327. Min Act: -0.0001

Data Index: 834219 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.3997. Min Range: -0.3997

Max Act: 0.2345. Min Act: -0.0001

Data Index: 901414 (C4 (Web Text))

Max Activating Token Index: 452