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

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

Neuron 2531 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.4831. Min Act: -0.0001

Data Index: 402180 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.2073. Min Act: -0.0001

Data Index: 1017930 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1500117 (Python Code)

Max Activating Token Index: 445

Text #3

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1071. Min Act: -0.0001

Data Index: 312319 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1785. Min Act: -0.0001

Data Index: 724675 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1269. Min Act: -0.0001

Data Index: 1283823 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0472. Min Act: -0.0001

Data Index: 133104 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1146. Min Act: -0.0001

Data Index: 301416 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0875. Min Act: -0.0001

Data Index: 1169191 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0493. Min Act: -0.0001

Data Index: 409793 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0757. Min Act: -0.0001

Data Index: 691867 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0709. Min Act: -0.0001

Data Index: 1075263 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1205. Min Act: -0.0001

Data Index: 480961 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0351. Min Act: -0.0001

Data Index: 965493 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1028. Min Act: -0.0001

Data Index: 147716 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.1010. Min Act: -0.0001

Data Index: 550241 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0321. Min Act: -0.0001

Data Index: 436658 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0247. Min Act: -0.0001

Data Index: 1162733 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0216. Min Act: -0.0001

Data Index: 599438 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 1.4831. Min Range: -1.4831

Max Act: 1.0455. Min Act: -0.0001

Data Index: 415055 (C4 (Web Text))

Max Activating Token Index: 610