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

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

Neuron 5650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0345. Min Range: -2.0345

Max Act: 2.0345. Min Act: -0.0000

Data Index: 642196 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1156989 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.7704. Min Act: -0.0000

Data Index: 583505 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.9628. Min Act: -0.0000

Data Index: 883724 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.8175. Min Act: -0.0000

Data Index: 382332 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5431. Min Act: -0.0000

Data Index: 720425 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1004196 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4386. Min Act: -0.0000

Data Index: 708468 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1181698 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4337. Min Act: -0.0000

Data Index: 915492 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4856. Min Act: -0.0000

Data Index: 471411 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4766. Min Act: -0.0000

Data Index: 873317 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1333133 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4643. Min Act: -0.0000

Data Index: 635881 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.5240. Min Act: -0.0000

Data Index: 487215 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4177. Min Act: -0.0000

Data Index: 800846 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4146. Min Act: -0.0000

Data Index: 408656 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.3659. Min Act: -0.0000

Data Index: 51517 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1348983 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 2.0345. Min Range: -2.0345

Max Act: 1.4032. Min Act: -0.0000

Data Index: 27689 (C4 (Web Text))

Max Activating Token Index: 675