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

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

Neuron 2114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3499. Min Range: -3.3499

Max Act: 3.3499. Min Act: -0.0000

Data Index: 1576948 (Python Code)

Max Activating Token Index: 931

Text #1

Max Range: 3.3499. Min Range: -3.3499

Max Act: 3.0463. Min Act: -0.0000

Data Index: 1536299 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.6724. Min Act: -0.0000

Data Index: 213798 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.7589. Min Act: -0.0000

Data Index: 1605508 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.7669. Min Act: -0.0000

Data Index: 842835 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.6308. Min Act: -0.0000

Data Index: 863564 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.3602. Min Act: -0.0000

Data Index: 1110486 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.4784. Min Act: -0.0000

Data Index: 516154 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.4282. Min Act: -0.0000

Data Index: 202669 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.2955. Min Act: -0.0000

Data Index: 1308204 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.3517. Min Act: -0.0000

Data Index: 1294695 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.4421. Min Act: -0.0000

Data Index: 761449 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.3161. Min Act: -0.0000

Data Index: 1597790 (Python Code)

Max Activating Token Index: 454

Text #13

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.1758. Min Act: -0.0000

Data Index: 38939 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.2485. Min Act: -0.0000

Data Index: 715502 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.2259. Min Act: -0.0000

Data Index: 675145 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.2315. Min Act: -0.0000

Data Index: 751143 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 3.3499. Min Range: -3.3499

Max Act: 1.9785. Min Act: -0.0000

Data Index: 950110 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.1866. Min Act: -0.0000

Data Index: 1201220 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 3.3499. Min Range: -3.3499

Max Act: 2.0906. Min Act: -0.0000

Data Index: 1116344 (C4 (Web Text))

Max Activating Token Index: 455