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

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

Neuron 3411 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.6493. Min Act: -0.0000

Data Index: 254286 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.5746. Min Act: -0.0000

Data Index: 337548 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.6028. Min Act: -0.0000

Data Index: 298546 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.5572. Min Act: -0.0000

Data Index: 899438 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4697. Min Act: -0.0000

Data Index: 783497 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4931. Min Act: -0.0000

Data Index: 123191 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4450. Min Act: -0.0000

Data Index: 336798 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4229. Min Act: -0.0000

Data Index: 856231 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1194012 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4033. Min Act: -0.0000

Data Index: 858842 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4459. Min Act: -0.0000

Data Index: 95924 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4678. Min Act: -0.0000

Data Index: 645264 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4249. Min Act: -0.0000

Data Index: 819948 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4131. Min Act: -0.0000

Data Index: 733187 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4513. Min Act: -0.0000

Data Index: 138016 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4035. Min Act: -0.0000

Data Index: 382052 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4090. Min Act: -0.0000

Data Index: 701067 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.4221. Min Act: -0.0000

Data Index: 756551 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.2705. Min Act: -0.0000

Data Index: 439089 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 1.6493. Min Range: -1.6493

Max Act: 1.3877. Min Act: -0.0000

Data Index: 788383 (C4 (Web Text))

Max Activating Token Index: 101