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

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

Neuron 418 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.7122. Min Act: -0.0001

Data Index: 903909 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6215. Min Act: -0.0000

Data Index: 306979 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.6024. Min Act: -0.0000

Data Index: 366652 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5992. Min Act: -0.0000

Data Index: 54754 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5657. Min Act: -0.0000

Data Index: 312610 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1166870 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5429. Min Act: -0.0000

Data Index: 452283 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5269. Min Act: -0.0000

Data Index: 259333 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5788. Min Act: -0.0001

Data Index: 591167 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5275. Min Act: -0.0000

Data Index: 280386 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.5244. Min Act: -0.0001

Data Index: 992341 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1188242 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4930. Min Act: -0.0000

Data Index: 302017 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1135849 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4902. Min Act: -0.0000

Data Index: 80877 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4664. Min Act: -0.0001

Data Index: 739218 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1359315 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4369. Min Act: -0.0000

Data Index: 246423 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4256. Min Act: -0.0001

Data Index: 1114165 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.7122. Min Range: -0.7122

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1251884 (C4 (Web Text))

Max Activating Token Index: 766