Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 373 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1320295 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2172. Min Act: -0.0001

Data Index: 919874 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2154. Min Act: -0.0001

Data Index: 382489 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2078. Min Act: -0.0001

Data Index: 562590 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2046. Min Act: -0.0001

Data Index: 33404 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1856. Min Act: -0.0001

Data Index: 556519 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1016461 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1144586 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1860. Min Act: -0.0001

Data Index: 964505 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1920. Min Act: -0.0001

Data Index: 309783 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1912. Min Act: -0.0001

Data Index: 329766 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1900. Min Act: -0.0001

Data Index: 714473 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1787. Min Act: -0.0001

Data Index: 573367 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1858. Min Act: -0.0001

Data Index: 894467 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1768. Min Act: -0.0001

Data Index: 558872 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1757. Min Act: -0.0001

Data Index: 1174137 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1771. Min Act: -0.0001

Data Index: 105761 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1749. Min Act: -0.0001

Data Index: 260270 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1755. Min Act: -0.0001

Data Index: 158184 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1875. Min Act: -0.0001

Data Index: 72948 (C4 (Web Text))

Max Activating Token Index: 606