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

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

Neuron 973 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0693. Min Range: -1.0693

Max Act: 1.0693. Min Act: -0.0001

Data Index: 1324284 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.0693. Min Range: -1.0693

Max Act: 1.0353. Min Act: -0.0001

Data Index: 844989 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 1.0693. Min Range: -1.0693

Max Act: 1.0006. Min Act: -0.0001

Data Index: 853631 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.9939. Min Act: -0.0001

Data Index: 751043 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.0693. Min Range: -1.0693

Max Act: 1.0180. Min Act: -0.0001

Data Index: 848918 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8660. Min Act: -0.0001

Data Index: 1332902 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.9379. Min Act: -0.0001

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8947. Min Act: -0.0001

Data Index: 462607 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.9038. Min Act: -0.0001

Data Index: 1329872 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8949. Min Act: -0.0001

Data Index: 559229 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8376. Min Act: -0.0001

Data Index: 147862 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8887. Min Act: -0.0001

Data Index: 1290701 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8580. Min Act: -0.0001

Data Index: 107503 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8587. Min Act: -0.0001

Data Index: 437016 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8240. Min Act: -0.0001

Data Index: 117349 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8951. Min Act: -0.0001

Data Index: 772522 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8553. Min Act: -0.0001

Data Index: 793735 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.7716. Min Act: -0.0001

Data Index: 419100 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8405. Min Act: -0.0001

Data Index: 444292 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 1.0693. Min Range: -1.0693

Max Act: 0.8154. Min Act: -0.0001

Data Index: 1058852 (C4 (Web Text))

Max Activating Token Index: 301