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

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

Neuron 2893 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: 1.2462. Min Range: -1.2462

Max Act: 1.2462. Min Act: -0.0001

Data Index: 753472 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0951. Min Act: -0.0001

Data Index: 541912 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0200. Min Act: -0.0001

Data Index: 1275234 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.2462. Min Range: -1.2462

Max Act: 1.0630. Min Act: -0.0001

Data Index: 415550 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9755. Min Act: -0.0001

Data Index: 862428 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9189. Min Act: -0.0001

Data Index: 113889 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.9318. Min Act: -0.0001

Data Index: 661661 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1046388 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8841. Min Act: -0.0001

Data Index: 317061 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8017. Min Act: -0.0001

Data Index: 164611 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8135. Min Act: -0.0001

Data Index: 427391 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8263. Min Act: -0.0001

Data Index: 608523 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.7726. Min Act: -0.0001

Data Index: 1067296 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1266683 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.7882. Min Act: -0.0001

Data Index: 1120745 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.7071. Min Act: -0.0001

Data Index: 663964 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.7775. Min Act: -0.0001

Data Index: 971055 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.7306. Min Act: -0.0001

Data Index: 772524 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.8361. Min Act: -0.0001

Data Index: 163969 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 1.2462. Min Range: -1.2462

Max Act: 0.7232. Min Act: -0.0001

Data Index: 435240 (C4 (Web Text))

Max Activating Token Index: 216