Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1263 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.3276. Min Act: -0.0003

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.2660. Min Act: -0.0003

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1975. Min Act: -0.0003

Data Index: 496670 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1631. Min Act: -0.0002

Data Index: 762393 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1511. Min Act: -0.0003

Data Index: 460420 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1429. Min Act: -0.0003

Data Index: 357321 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.1310. Min Act: -0.0003

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0965. Min Act: -0.0003

Data Index: 1038541 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0733. Min Act: -0.0003

Data Index: 1311934 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0968. Min Act: -0.0003

Data Index: 367081 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0884. Min Act: -0.0003

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0819. Min Act: -0.0003

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0660. Min Act: -0.0003

Data Index: 224049 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0349. Min Act: -0.0003

Data Index: 294399 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0621. Min Act: -0.0003

Data Index: 473014 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0606. Min Act: -0.0003

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0563. Min Act: -0.0003

Data Index: 470097 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0878. Min Act: -0.0002

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0206. Min Act: -0.0002

Data Index: 919051 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.3276. Min Range: -1.3276

Max Act: 1.0332. Min Act: -0.0003

Data Index: 1340669 (C4 (Web Text))

Max Activating Token Index: 117