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

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

Neuron 645 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: 1.6975. Min Range: -1.6975

Max Act: 1.5390. Min Act: -0.0001

Data Index: 866436 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.4783. Min Act: -0.0001

Data Index: 143986 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.6975. Min Act: -0.0001

Data Index: 1231080 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.6625. Min Act: -0.0001

Data Index: 233090 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.3894. Min Act: -0.0001

Data Index: 1007266 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.4631. Min Act: -0.0001

Data Index: 824349 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.3118. Min Act: -0.0001

Data Index: 57943 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.2622. Min Act: -0.0001

Data Index: 267950 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.3402. Min Act: -0.0001

Data Index: 637449 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.2127. Min Act: -0.0001

Data Index: 516494 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.2360. Min Act: -0.0001

Data Index: 603507 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.1476. Min Act: -0.0001

Data Index: 1153334 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.1505. Min Act: -0.0001

Data Index: 1312318 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.0802. Min Act: -0.0001

Data Index: 1011133 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.1169. Min Act: -0.0001

Data Index: 209123 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.6975. Min Range: -1.6975

Max Act: 0.9591. Min Act: -0.0001

Data Index: 592164 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.1461. Min Act: -0.0001

Data Index: 681455 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.0724. Min Act: -0.0001

Data Index: 1265420 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.1351. Min Act: -0.0001

Data Index: 791473 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.6975. Min Range: -1.6975

Max Act: 1.0915. Min Act: -0.0001

Data Index: 251519 (C4 (Web Text))

Max Activating Token Index: 760