Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1295. Min Act: -0.0003

Data Index: 243253 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1210. Min Act: -0.0003

Data Index: 784940 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1214. Min Act: -0.0003

Data Index: 75857 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1195. Min Act: -0.0003

Data Index: 855302 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1154. Min Act: -0.0003

Data Index: 621163 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1196. Min Act: -0.0003

Data Index: 1297329 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1145. Min Act: -0.0004

Data Index: 369195 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1123. Min Act: -0.0004

Data Index: 891984 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1100. Min Act: -0.0003

Data Index: 1218903 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0994. Min Act: -0.0003

Data Index: 856449 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1034. Min Act: -0.0003

Data Index: 336268 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1025. Min Act: -0.0003

Data Index: 551883 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0983. Min Act: -0.0003

Data Index: 359968 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0973. Min Act: -0.0004

Data Index: 389048 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0967. Min Act: -0.0003

Data Index: 369715 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0967. Min Act: -0.0003

Data Index: 345085 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.1027. Min Act: -0.0004

Data Index: 1007897 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0956. Min Act: -0.0003

Data Index: 421478 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0954. Min Act: -0.0003

Data Index: 559524 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1295. Min Range: -0.1295

Max Act: 0.0972. Min Act: -0.0003

Data Index: 526997 (C4 (Web Text))

Max Activating Token Index: 81