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

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

Neuron 1367 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1218092 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.3361. Min Act: -0.0000

Data Index: 319680 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.3447. Min Act: -0.0000

Data Index: 433901 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.2745. Min Act: -0.0000

Data Index: 965180 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.3102. Min Act: -0.0000

Data Index: 936090 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.3131. Min Act: -0.0000

Data Index: 769029 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1430. Min Act: -0.0000

Data Index: 1300591 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.2085. Min Act: -0.0000

Data Index: 4611 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1176358 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.0849. Min Act: -0.0000

Data Index: 76392 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1462. Min Act: -0.0000

Data Index: 366298 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1478. Min Act: -0.0000

Data Index: 991392 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.0833. Min Act: -0.0001

Data Index: 717048 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.9739. Min Act: -0.0000

Data Index: 75809 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1240. Min Act: -0.0000

Data Index: 904420 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.0600. Min Act: -0.0000

Data Index: 988548 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.0107. Min Act: -0.0000

Data Index: 43025 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1295080 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.9112. Min Act: -0.0000

Data Index: 166222 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.9847. Min Act: -0.0000

Data Index: 811806 (C4 (Web Text))

Max Activating Token Index: 45