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

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

Neuron 4652 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9332. Min Range: -3.9332

Max Act: 3.9332. Min Act: -0.0000

Data Index: 619079 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.8813. Min Act: -0.0000

Data Index: 897791 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.7283. Min Act: -0.0000

Data Index: 1041970 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.7977. Min Act: -0.0000

Data Index: 889733 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.6437. Min Act: -0.0000

Data Index: 1266996 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.4925. Min Act: -0.0000

Data Index: 1245435 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.8506. Min Act: -0.0000

Data Index: 999462 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.6019. Min Act: -0.0000

Data Index: 647627 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.5333. Min Act: -0.0000

Data Index: 997401 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.4728. Min Act: -0.0000

Data Index: 120184 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.3414. Min Act: -0.0000

Data Index: 707773 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.3036. Min Act: -0.0000

Data Index: 499375 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.4387. Min Act: -0.0000

Data Index: 660938 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.4297. Min Act: -0.0000

Data Index: 408056 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.5587. Min Act: -0.0000

Data Index: 1230941 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.3486. Min Act: -0.0000

Data Index: 623863 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.1916. Min Act: -0.0000

Data Index: 928604 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1122872 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.1723. Min Act: -0.0000

Data Index: 802159 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 3.9332. Min Range: -3.9332

Max Act: 2.2633. Min Act: -0.0000

Data Index: 470908 (C4 (Web Text))

Max Activating Token Index: 596