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

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

Neuron 3965 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.8288. Min Act: -0.0002

Data Index: 996180 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.8294. Min Act: -0.0001

Data Index: 1209403 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6736. Min Act: -0.0002

Data Index: 211115 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6856. Min Act: -0.0002

Data Index: 892580 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7064. Min Act: -0.0002

Data Index: 801561 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.5985. Min Act: -0.0001

Data Index: 1290558 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6745. Min Act: -0.0001

Data Index: 581671 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6633. Min Act: -0.0002

Data Index: 169582 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6414. Min Act: -0.0001

Data Index: 362843 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.7058. Min Act: -0.0001

Data Index: 673803 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6446. Min Act: -0.0002

Data Index: 795900 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6646. Min Act: -0.0002

Data Index: 435375 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6545. Min Act: -0.0001

Data Index: 1212738 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6366. Min Act: -0.0001

Data Index: 1258461 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1315964 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6508. Min Act: -0.0001

Data Index: 285832 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6221. Min Act: -0.0001

Data Index: 226827 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6225. Min Act: -0.0001

Data Index: 742521 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6176. Min Act: -0.0001

Data Index: 724778 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.8294. Min Range: -0.8294

Max Act: 0.6311. Min Act: -0.0001

Data Index: 257263 (C4 (Web Text))

Max Activating Token Index: 999