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

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

Neuron 4171 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.9206. Min Act: -0.0000

Data Index: 116981 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 3.0865. Min Range: -3.0865

Max Act: 3.0073. Min Act: -0.0000

Data Index: 389945 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.9862. Min Act: -0.0000

Data Index: 350219 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.9402. Min Act: -0.0000

Data Index: 417004 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 3.0865. Min Range: -3.0865

Max Act: 3.0865. Min Act: -0.0000

Data Index: 714798 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6204. Min Act: -0.0000

Data Index: 697829 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 3.0865. Min Range: -3.0865

Max Act: 3.0491. Min Act: -0.0000

Data Index: 412796 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.8981. Min Act: -0.0000

Data Index: 255881 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.7871. Min Act: -0.0000

Data Index: 206683 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.7982. Min Act: -0.0000

Data Index: 734367 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.7307. Min Act: -0.0000

Data Index: 1139036 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.5720. Min Act: -0.0000

Data Index: 263227 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6989. Min Act: -0.0000

Data Index: 197502 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6710. Min Act: -0.0000

Data Index: 1209191 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6862. Min Act: -0.0000

Data Index: 591394 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6606. Min Act: -0.0000

Data Index: 121801 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.5221. Min Act: -0.0000

Data Index: 1011038 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.6330. Min Act: -0.0000

Data Index: 635460 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.5977. Min Act: -0.0000

Data Index: 192443 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 3.0865. Min Range: -3.0865

Max Act: 2.4925. Min Act: -0.0000

Data Index: 162714 (C4 (Web Text))

Max Activating Token Index: 316