Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 796 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1508. Min Act: -0.0002

Data Index: 779695 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1510. Min Act: -0.0002

Data Index: 1057646 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1436. Min Act: -0.0002

Data Index: 823332 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1184745 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1183288 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1159725 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1320722 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1207. Min Act: -0.0002

Data Index: 90373 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1218. Min Act: -0.0002

Data Index: 670152 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1241. Min Act: -0.0002

Data Index: 42244 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1153. Min Act: -0.0002

Data Index: 896359 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1136. Min Act: -0.0002

Data Index: 443242 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1086565 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1107. Min Act: -0.0002

Data Index: 625048 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1070. Min Act: -0.0002

Data Index: 37502 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1062. Min Act: -0.0002

Data Index: 13386 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1200262 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1120. Min Act: -0.0002

Data Index: 229878 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1088. Min Act: -0.0002

Data Index: 640580 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.1510. Min Range: -0.1510

Max Act: 0.1060. Min Act: -0.0002

Data Index: 599360 (C4 (Web Text))

Max Activating Token Index: 615