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

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

Neuron 411 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: 3.5174. Min Range: -3.5174

Max Act: 3.5174. Min Act: -0.0001

Data Index: 217911 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2693. Min Act: -0.0001

Data Index: 1094286 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2457. Min Act: -0.0001

Data Index: 385682 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.4920. Min Act: -0.0001

Data Index: 512372 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.2712. Min Act: -0.0001

Data Index: 845161 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.1724. Min Act: -0.0001

Data Index: 74706 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.0227. Min Act: -0.0001

Data Index: 42450 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.8604. Min Act: -0.0001

Data Index: 462586 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 3.5174. Min Range: -3.5174

Max Act: 3.1222. Min Act: -0.0001

Data Index: 996206 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.6725. Min Act: -0.0001

Data Index: 1221301 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.9432. Min Act: -0.0001

Data Index: 161638 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.5917. Min Act: -0.0001

Data Index: 774190 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.6979. Min Act: -0.0001

Data Index: 245321 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.6951. Min Act: -0.0001

Data Index: 624490 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.6588. Min Act: -0.0001

Data Index: 968508 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.7550. Min Act: -0.0001

Data Index: 1314985 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.4919. Min Act: -0.0001

Data Index: 1206476 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.4729. Min Act: -0.0001

Data Index: 1077329 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.5904. Min Act: -0.0001

Data Index: 259504 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 3.5174. Min Range: -3.5174

Max Act: 2.5623. Min Act: -0.0001

Data Index: 1259305 (C4 (Web Text))

Max Activating Token Index: 615