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

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

Neuron 231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.8724. Min Act: -0.0000

Data Index: 1635626 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.4327. Min Act: -0.0000

Data Index: 508943 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.3007. Min Act: -0.0000

Data Index: 1650284 (Python Code)

Max Activating Token Index: 331

Text #3

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.0944. Min Act: -0.0000

Data Index: 771853 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.3230. Min Act: -0.0000

Data Index: 799967 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.1334. Min Act: -0.0000

Data Index: 743015 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.8476. Min Act: -0.0000

Data Index: 1509500 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.9258. Min Act: -0.0000

Data Index: 88747 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.1448. Min Act: -0.0000

Data Index: 931921 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.8912. Min Act: -0.0000

Data Index: 857223 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.2318. Min Act: -0.0000

Data Index: 269473 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.8956. Min Act: -0.0000

Data Index: 1139753 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.9995. Min Act: -0.0001

Data Index: 1629157 (Python Code)

Max Activating Token Index: 667

Text #13

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.9846. Min Act: -0.0000

Data Index: 699185 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.9422. Min Act: -0.0000

Data Index: 1133860 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.0663. Min Act: -0.0000

Data Index: 1187748 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 2.8724. Min Range: -2.8724

Max Act: 1.9288. Min Act: -0.0000

Data Index: 766134 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.0541. Min Act: -0.0000

Data Index: 26361 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.1384. Min Act: -0.0000

Data Index: 1503648 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 2.8724. Min Range: -2.8724

Max Act: 2.0608. Min Act: -0.0000

Data Index: 764750 (C4 (Web Text))

Max Activating Token Index: 475