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

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

Neuron 4471 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: 3.8643. Min Range: -3.8643

Max Act: 3.8290. Min Act: -0.0000

Data Index: 29049 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.8643. Min Act: -0.0000

Data Index: 498315 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.7919. Min Act: -0.0000

Data Index: 845095 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.7698. Min Act: -0.0000

Data Index: 829478 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.6640. Min Act: -0.0000

Data Index: 373763 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.5636. Min Act: -0.0000

Data Index: 752997 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.5051. Min Act: -0.0000

Data Index: 36526 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.4651. Min Act: -0.0000

Data Index: 1223767 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.3090. Min Act: -0.0000

Data Index: 62241 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.4545. Min Act: -0.0000

Data Index: 1346665 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.4423. Min Act: -0.0000

Data Index: 609999 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.4358. Min Act: -0.0000

Data Index: 940674 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.2649. Min Act: -0.0000

Data Index: 1229021 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.3527. Min Act: -0.0000

Data Index: 75506 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.3397. Min Act: -0.0000

Data Index: 1003026 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.1416. Min Act: -0.0000

Data Index: 776004 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 3.8643. Min Range: -3.8643

Max Act: 3.0258. Min Act: -0.0000

Data Index: 697111 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 3.8643. Min Range: -3.8643

Max Act: 2.9894. Min Act: -0.0000

Data Index: 1103278 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 3.8643. Min Range: -3.8643

Max Act: 2.9437. Min Act: -0.0000

Data Index: 1233910 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 3.8643. Min Range: -3.8643

Max Act: 2.9440. Min Act: -0.0000

Data Index: 167879 (C4 (Web Text))

Max Activating Token Index: 338