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

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

Neuron 3256 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: 2.2181. Min Range: -2.2181

Max Act: 2.2181. Min Act: -0.0001

Data Index: 1191809 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 2.2181. Min Range: -2.2181

Max Act: 2.0734. Min Act: -0.0001

Data Index: 172619 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4542. Min Act: -0.0001

Data Index: 1247519 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6916. Min Act: -0.0001

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5529. Min Act: -0.0001

Data Index: 610888 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7353. Min Act: -0.0001

Data Index: 509714 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.7290. Min Act: -0.0001

Data Index: 974027 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.6640. Min Act: -0.0001

Data Index: 747949 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5486. Min Act: -0.0001

Data Index: 1059233 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5286. Min Act: -0.0001

Data Index: 1221404 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5374. Min Act: -0.0001

Data Index: 850323 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4395. Min Act: -0.0001

Data Index: 1333235 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5091. Min Act: -0.0001

Data Index: 740922 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5800. Min Act: -0.0001

Data Index: 126371 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.5849. Min Act: -0.0001

Data Index: 553979 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4881. Min Act: -0.0001

Data Index: 1331451 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.3907. Min Act: -0.0001

Data Index: 1123478 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4701. Min Act: -0.0001

Data Index: 695307 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4947. Min Act: -0.0001

Data Index: 117356 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 2.2181. Min Range: -2.2181

Max Act: 1.4451. Min Act: -0.0001

Data Index: 155704 (C4 (Web Text))

Max Activating Token Index: 968