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

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

Neuron 690 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: 1.8381. Min Range: -1.8381

Max Act: 1.8381. Min Act: -0.0001

Data Index: 806984 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.5684. Min Act: -0.0001

Data Index: 366582 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3012. Min Act: -0.0001

Data Index: 812855 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.4561. Min Act: -0.0001

Data Index: 496193 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3656. Min Act: -0.0001

Data Index: 1071359 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3676. Min Act: -0.0001

Data Index: 1137891 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.1823. Min Act: -0.0001

Data Index: 508654 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2133. Min Act: -0.0001

Data Index: 222122 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2079. Min Act: -0.0001

Data Index: 288330 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.1350. Min Act: -0.0001

Data Index: 1246193 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2177. Min Act: -0.0001

Data Index: 12803 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2426. Min Act: -0.0001

Data Index: 352264 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2247. Min Act: -0.0001

Data Index: 1332174 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.1889. Min Act: -0.0001

Data Index: 1344890 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.0851. Min Act: -0.0001

Data Index: 972275 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.1126. Min Act: -0.0001

Data Index: 241058 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.2064. Min Act: -0.0001

Data Index: 1017548 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.0834. Min Act: -0.0001

Data Index: 292087 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.0765. Min Act: -0.0001

Data Index: 1183319 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 1.8381. Min Range: -1.8381

Max Act: 1.3033. Min Act: -0.0001

Data Index: 247289 (C4 (Web Text))

Max Activating Token Index: 765