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

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

Neuron 5878 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.8946. Min Act: -0.0001

Data Index: 42776 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6483. Min Act: -0.0001

Data Index: 646346 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6643. Min Act: -0.0001

Data Index: 976274 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.7054. Min Act: -0.0001

Data Index: 1119252 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.7189. Min Act: -0.0001

Data Index: 519797 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.7176. Min Act: -0.0001

Data Index: 753950 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1057893 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6591. Min Act: -0.0001

Data Index: 951139 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5982. Min Act: -0.0001

Data Index: 1276000 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6367. Min Act: -0.0001

Data Index: 1073112 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6048. Min Act: -0.0001

Data Index: 625772 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5615. Min Act: -0.0001

Data Index: 120095 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6127. Min Act: -0.0001

Data Index: 663426 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6047. Min Act: -0.0001

Data Index: 898721 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6024. Min Act: -0.0001

Data Index: 91504 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5784. Min Act: -0.0001

Data Index: 14087 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5675. Min Act: -0.0001

Data Index: 286848 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.6195. Min Act: -0.0001

Data Index: 226035 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5907. Min Act: -0.0001

Data Index: 1215668 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.8946. Min Range: -0.8946

Max Act: 0.5687. Min Act: -0.0001

Data Index: 130856 (C4 (Web Text))

Max Activating Token Index: 449