Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3658 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.6348. Min Act: -0.0001

Data Index: 1273475 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.6099. Min Act: -0.0001

Data Index: 249171 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.4707. Min Act: -0.0001

Data Index: 851023 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.4359. Min Act: -0.0001

Data Index: 560947 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.5195. Min Act: -0.0001

Data Index: 363792 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.4869. Min Act: -0.0001

Data Index: 540711 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.3445. Min Act: -0.0001

Data Index: 1223131 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.3695. Min Act: -0.0001

Data Index: 462507 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.4264. Min Act: -0.0001

Data Index: 309668 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.4428. Min Act: -0.0001

Data Index: 1059866 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.3951. Min Act: -0.0001

Data Index: 1011205 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.3866. Min Act: -0.0001

Data Index: 58996 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.2262. Min Act: -0.0001

Data Index: 712830 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.4534. Min Act: -0.0001

Data Index: 965675 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.2517. Min Act: -0.0001

Data Index: 207637 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.2765. Min Act: -0.0001

Data Index: 1040707 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.2860. Min Act: -0.0001

Data Index: 995843 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.2854. Min Act: -0.0001

Data Index: 287351 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.4325. Min Act: -0.0001

Data Index: 1471514 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 1.6348. Min Range: -1.6348

Max Act: 1.2364. Min Act: -0.0001

Data Index: 1152182 (C4 (Web Text))

Max Activating Token Index: 269