Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2884 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.1573. Min Act: -0.0001

Data Index: 425039 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.1139. Min Act: -0.0001

Data Index: 502600 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.0933. Min Act: -0.0001

Data Index: 504035 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.0235. Min Act: -0.0001

Data Index: 846844 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.0215. Min Act: -0.0001

Data Index: 5619 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.1573. Min Range: -1.1573

Max Act: 1.0938. Min Act: -0.0001

Data Index: 560787 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1063232 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9638. Min Act: -0.0001

Data Index: 661995 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9612. Min Act: -0.0001

Data Index: 969352 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9242. Min Act: -0.0001

Data Index: 43716 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9121. Min Act: -0.0001

Data Index: 793268 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.9369. Min Act: -0.0001

Data Index: 1003788 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8543. Min Act: -0.0001

Data Index: 1324457 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8856. Min Act: -0.0001

Data Index: 237181 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8606. Min Act: -0.0001

Data Index: 74940 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8244. Min Act: -0.0001

Data Index: 1161991 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8276. Min Act: -0.0001

Data Index: 99009 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8561. Min Act: -0.0001

Data Index: 948482 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8524. Min Act: -0.0001

Data Index: 1224041 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.1573. Min Range: -1.1573

Max Act: 0.8710. Min Act: -0.0001

Data Index: 212343 (C4 (Web Text))

Max Activating Token Index: 153