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

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

Neuron 3392 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: 0.7811. Min Range: -0.7811

Max Act: 0.7811. Min Act: -0.0001

Data Index: 627614 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7426. Min Act: -0.0001

Data Index: 284539 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7473. Min Act: -0.0000

Data Index: 982312 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7403. Min Act: -0.0000

Data Index: 2935 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7468. Min Act: -0.0000

Data Index: 838692 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7293. Min Act: -0.0000

Data Index: 443402 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7241. Min Act: -0.0000

Data Index: 559670 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6971. Min Act: -0.0001

Data Index: 521594 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7168. Min Act: -0.0001

Data Index: 1005566 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1025764 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7505. Min Act: -0.0000

Data Index: 773569 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6756. Min Act: -0.0001

Data Index: 113823 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6741. Min Act: -0.0001

Data Index: 233986 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6443. Min Act: -0.0001

Data Index: 689278 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6883. Min Act: -0.0001

Data Index: 133262 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.7089. Min Act: -0.0001

Data Index: 553535 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1333337 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6602. Min Act: -0.0000

Data Index: 714806 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6562. Min Act: -0.0001

Data Index: 172280 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.7811. Min Range: -0.7811

Max Act: 0.6573. Min Act: -0.0000

Data Index: 185713 (C4 (Web Text))

Max Activating Token Index: 820