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

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

Neuron 2645 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1637. Min Act: -0.0001

Data Index: 849019 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1308324 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1678. Min Act: -0.0001

Data Index: 665313 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1476. Min Act: -0.0001

Data Index: 516406 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1382. Min Act: -0.0001

Data Index: 663779 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1166486 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1271. Min Act: -0.0001

Data Index: 860392 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1139. Min Act: -0.0001

Data Index: 328089 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1054. Min Act: -0.0001

Data Index: 556495 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1115. Min Act: -0.0001

Data Index: 231277 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1168116 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1416220 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0944. Min Act: -0.0001

Data Index: 802051 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1052201 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1061994 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0950. Min Act: -0.0001

Data Index: 887181 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0905. Min Act: -0.0000

Data Index: 109714 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0954. Min Act: -0.0001

Data Index: 741654 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0947. Min Act: -0.0001

Data Index: 620595 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.1678. Min Range: -0.1678

Max Act: 0.0916. Min Act: -0.0001

Data Index: 993312 (C4 (Web Text))

Max Activating Token Index: 525