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

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

Neuron 4248 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.8364. Min Act: -0.0001

Data Index: 953976 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.8202. Min Act: -0.0001

Data Index: 10394 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5786. Min Act: -0.0001

Data Index: 869477 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6517. Min Act: -0.0001

Data Index: 468366 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6576. Min Act: -0.0001

Data Index: 687204 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6503. Min Act: -0.0001

Data Index: 1238907 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5677. Min Act: -0.0001

Data Index: 249810 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5891. Min Act: -0.0001

Data Index: 807090 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6290. Min Act: -0.0001

Data Index: 243949 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5546. Min Act: -0.0001

Data Index: 1195074 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5686. Min Act: -0.0002

Data Index: 202068 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5560. Min Act: -0.0002

Data Index: 39900 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5569. Min Act: -0.0001

Data Index: 438050 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5190. Min Act: -0.0001

Data Index: 1156702 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5599. Min Act: -0.0001

Data Index: 681502 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5985. Min Act: -0.0001

Data Index: 800637 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.6060. Min Act: -0.0001

Data Index: 543031 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5359. Min Act: -0.0001

Data Index: 991682 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5598. Min Act: -0.0001

Data Index: 506719 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.8364. Min Range: -0.8364

Max Act: 0.5454. Min Act: -0.0001

Data Index: 1327255 (C4 (Web Text))

Max Activating Token Index: 206