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

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

Neuron 1535 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5679. Min Act: -0.0001

Data Index: 1128056 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5392. Min Act: -0.0001

Data Index: 845069 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5206. Min Act: -0.0001

Data Index: 328253 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5523. Min Act: -0.0001

Data Index: 679209 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5615. Min Act: -0.0001

Data Index: 1234806 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5298. Min Act: -0.0001

Data Index: 1215076 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5336. Min Act: -0.0001

Data Index: 417600 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5010. Min Act: -0.0001

Data Index: 970972 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5074. Min Act: -0.0001

Data Index: 512834 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4965. Min Act: -0.0001

Data Index: 866805 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5283. Min Act: -0.0001

Data Index: 954889 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4948. Min Act: -0.0001

Data Index: 445130 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1255166 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5052. Min Act: -0.0001

Data Index: 841965 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4577. Min Act: -0.0001

Data Index: 668716 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.5018. Min Act: -0.0001

Data Index: 329266 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4707. Min Act: -0.0001

Data Index: 90986 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4682. Min Act: -0.0001

Data Index: 206210 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4243. Min Act: -0.0001

Data Index: 801155 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.5679. Min Range: -0.5679

Max Act: 0.4636. Min Act: -0.0001

Data Index: 1084733 (C4 (Web Text))

Max Activating Token Index: 56