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

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

Neuron 4600 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2810. Min Act: -0.0001

Data Index: 226845 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2782. Min Act: -0.0001

Data Index: 285267 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2419. Min Act: -0.0001

Data Index: 1067624 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2366. Min Act: -0.0001

Data Index: 766209 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2368. Min Act: -0.0001

Data Index: 258412 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1076505 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2224. Min Act: -0.0001

Data Index: 1295498 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2101. Min Act: -0.0001

Data Index: 76844 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2102. Min Act: -0.0001

Data Index: 641411 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2035. Min Act: -0.0001

Data Index: 388400 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2066. Min Act: -0.0001

Data Index: 394981 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2042. Min Act: -0.0001

Data Index: 1214914 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1032139 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1005309 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.1999. Min Act: -0.0001

Data Index: 593874 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.1986. Min Act: -0.0001

Data Index: 838607 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.1776. Min Act: -0.0001

Data Index: 239104 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.1775. Min Act: -0.0001

Data Index: 432614 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.1963. Min Act: -0.0001

Data Index: 754482 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.2810. Min Range: -0.2810

Max Act: 0.1969. Min Act: -0.0001

Data Index: 977513 (C4 (Web Text))

Max Activating Token Index: 422