Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2365. Min Range: -3.2365

Max Act: 3.2365. Min Act: -0.0000

Data Index: 1085776 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.9293. Min Act: 0.0000

Data Index: 653129 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.2365. Min Range: -3.2365

Max Act: 3.2212. Min Act: 0.0000

Data Index: 608516 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.8400. Min Act: -0.0000

Data Index: 991198 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.9852. Min Act: -0.0000

Data Index: 713111 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.9523. Min Act: -0.0000

Data Index: 379352 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.8702. Min Act: -0.0000

Data Index: 1007220 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.6788. Min Act: -0.0000

Data Index: 6207 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.8226. Min Act: -0.0000

Data Index: 239166 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.8048. Min Act: 0.0000

Data Index: 21224 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.6294. Min Act: -0.0000

Data Index: 666791 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.5867. Min Act: -0.0000

Data Index: 1014290 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.8176. Min Act: -0.0000

Data Index: 1170582 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.8058. Min Act: -0.0000

Data Index: 868553 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.8137. Min Act: 0.0000

Data Index: 64982 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.4885. Min Act: -0.0000

Data Index: 360496 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.6159. Min Act: -0.0000

Data Index: 764164 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.6119. Min Act: -0.0000

Data Index: 1135112 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.3643. Min Act: -0.0000

Data Index: 1379 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 3.2365. Min Range: -3.2365

Max Act: 2.7379. Min Act: -0.0000

Data Index: 797333 (C4 (Web Text))

Max Activating Token Index: 887