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

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

Neuron 1718 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: 3.2645. Min Range: -3.2645

Max Act: 3.2645. Min Act: -0.0001

Data Index: 167838 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 3.2645. Min Range: -3.2645

Max Act: 3.0638. Min Act: -0.0001

Data Index: 154630 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.4245. Min Act: -0.0001

Data Index: 610370 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.9413. Min Act: -0.0001

Data Index: 79530 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.1171. Min Act: -0.0001

Data Index: 1317887 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.6748. Min Act: -0.0001

Data Index: 1183723 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.4755. Min Act: -0.0001

Data Index: 866103 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 3.2645. Min Range: -3.2645

Max Act: 1.9959. Min Act: -0.0001

Data Index: 1334392 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.4240. Min Act: -0.0001

Data Index: 871801 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.6725. Min Act: -0.0001

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.3911. Min Act: -0.0001

Data Index: 855036 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.4038. Min Act: -0.0001

Data Index: 261143 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.2847. Min Act: -0.0001

Data Index: 65195 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.4848. Min Act: -0.0001

Data Index: 666256 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.4869. Min Act: -0.0001

Data Index: 388690 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.1283. Min Act: -0.0001

Data Index: 53066 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.4279. Min Act: -0.0001

Data Index: 487877 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.3099. Min Act: -0.0001

Data Index: 154554 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.3839. Min Act: -0.0001

Data Index: 679380 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 3.2645. Min Range: -3.2645

Max Act: 2.1823. Min Act: -0.0001

Data Index: 1271256 (C4 (Web Text))

Max Activating Token Index: 653