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

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

Neuron 2350 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: 0.8263. Min Range: -0.8263

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1095949 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.8112. Min Act: -0.0001

Data Index: 1050857 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.8113. Min Act: -0.0001

Data Index: 815789 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7886. Min Act: -0.0001

Data Index: 764194 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1096296 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7214. Min Act: -0.0001

Data Index: 1074248 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7475. Min Act: -0.0001

Data Index: 806930 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1315394 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7099. Min Act: -0.0001

Data Index: 1320529 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7270. Min Act: -0.0001

Data Index: 44051 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6798. Min Act: -0.0001

Data Index: 886281 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6992. Min Act: -0.0001

Data Index: 1218390 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.7223. Min Act: -0.0001

Data Index: 1210311 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6541. Min Act: -0.0001

Data Index: 110049 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6734. Min Act: -0.0001

Data Index: 462912 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6449. Min Act: -0.0001

Data Index: 490139 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6693. Min Act: -0.0001

Data Index: 302898 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6668. Min Act: -0.0001

Data Index: 309228 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6632. Min Act: -0.0001

Data Index: 9396 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.8263. Min Range: -0.8263

Max Act: 0.6839. Min Act: -0.0001

Data Index: 106353 (C4 (Web Text))

Max Activating Token Index: 377