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

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

Neuron 1340 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: 1.7177. Min Range: -1.7177

Max Act: 1.7177. Min Act: -0.0001

Data Index: 342857 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.4200. Min Act: -0.0001

Data Index: 90709 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.3966. Min Act: -0.0001

Data Index: 441652 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.3043. Min Act: -0.0001

Data Index: 405744 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1273. Min Act: -0.0001

Data Index: 74240 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1923. Min Act: -0.0001

Data Index: 379230 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0748. Min Act: -0.0001

Data Index: 1260231 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1676. Min Act: -0.0001

Data Index: 1172271 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.2052. Min Act: -0.0001

Data Index: 1329576 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1787. Min Act: -0.0001

Data Index: 1074596 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0690. Min Act: -0.0001

Data Index: 615606 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.2146. Min Act: -0.0001

Data Index: 79174 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0468. Min Act: -0.0001

Data Index: 628769 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0136. Min Act: -0.0001

Data Index: 724967 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.7177. Min Range: -1.7177

Max Act: 0.8879. Min Act: -0.0001

Data Index: 1176496 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0356. Min Act: -0.0001

Data Index: 510398 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.7177. Min Range: -1.7177

Max Act: 0.9088. Min Act: -0.0001

Data Index: 731913 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.7177. Min Range: -1.7177

Max Act: 0.9262. Min Act: -0.0001

Data Index: 470149 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.7177. Min Range: -1.7177

Max Act: 0.9779. Min Act: -0.0001

Data Index: 361081 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.7177. Min Range: -1.7177

Max Act: 0.9016. Min Act: -0.0001

Data Index: 81560 (C4 (Web Text))

Max Activating Token Index: 232