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

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

Neuron 2309 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: 0.1600. Min Range: -0.1600

Max Act: 0.1321. Min Act: -0.0001

Data Index: 423726 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1038. Min Act: -0.0001

Data Index: 549663 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1147054 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1076. Min Act: -0.0001

Data Index: 469554 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1197. Min Act: -0.0001

Data Index: 275441 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1167496 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1330. Min Act: -0.0001

Data Index: 696400 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1178725 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1304. Min Act: -0.0001

Data Index: 1168114 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1501. Min Act: -0.0001

Data Index: 787016 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1121. Min Act: -0.0001

Data Index: 864534 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1323. Min Act: -0.0001

Data Index: 163433 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1101. Min Act: -0.0001

Data Index: 441571 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1321262 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1082056 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1079025 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1227. Min Act: -0.0001

Data Index: 183676 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1113077 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1328087 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.0982. Min Act: -0.0001

Data Index: 89322 (C4 (Web Text))

Max Activating Token Index: 906