Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.6020. Min Act: -0.0000

Data Index: 413697 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4609. Min Act: -0.0000

Data Index: 983116 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1147740 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4809. Min Act: -0.0000

Data Index: 316944 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4173. Min Act: -0.0000

Data Index: 283572 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1154645 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4722. Min Act: -0.0000

Data Index: 889409 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1306167 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4589. Min Act: -0.0000

Data Index: 875706 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4222. Min Act: -0.0000

Data Index: 251867 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1301403 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4286. Min Act: -0.0000

Data Index: 100449 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4294. Min Act: -0.0000

Data Index: 687313 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4271. Min Act: -0.0000

Data Index: 802230 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1201423 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4718. Min Act: -0.0000

Data Index: 936838 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.3982. Min Act: -0.0000

Data Index: 176103 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1034058 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.4391. Min Act: -0.0000

Data Index: 450228 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.6020. Min Range: -0.6020

Max Act: 0.3920. Min Act: -0.0000

Data Index: 721659 (C4 (Web Text))

Max Activating Token Index: 77