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

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

Neuron 3189 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2831. Min Range: -2.2831

Max Act: 2.0527. Min Act: -0.0000

Data Index: 1092694 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 2.2831. Min Range: -2.2831

Max Act: 2.2831. Min Act: -0.0000

Data Index: 1261527 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 2.2831. Min Range: -2.2831

Max Act: 2.0277. Min Act: -0.0000

Data Index: 1312531 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 2.2831. Min Range: -2.2831

Max Act: 2.0216. Min Act: -0.0000

Data Index: 200443 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 2.2831. Min Range: -2.2831

Max Act: 2.1237. Min Act: -0.0000

Data Index: 1118187 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 2.2831. Min Range: -2.2831

Max Act: 2.1256. Min Act: -0.0000

Data Index: 230558 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.8797. Min Act: -0.0000

Data Index: 1307066 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.9676. Min Act: -0.0000

Data Index: 647643 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.9440. Min Act: -0.0000

Data Index: 866773 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.9090. Min Act: -0.0000

Data Index: 324889 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.6216. Min Act: -0.0000

Data Index: 873809 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.8158. Min Act: -0.0000

Data Index: 1265638 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.8130. Min Act: -0.0000

Data Index: 692633 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.6975. Min Act: -0.0000

Data Index: 767668 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.8968. Min Act: -0.0000

Data Index: 463952 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.7893. Min Act: -0.0000

Data Index: 1238 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.7690. Min Act: -0.0000

Data Index: 607645 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.7775. Min Act: -0.0000

Data Index: 588533 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.8562. Min Act: -0.0000

Data Index: 639623 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 2.2831. Min Range: -2.2831

Max Act: 1.8344. Min Act: -0.0000

Data Index: 878150 (C4 (Web Text))

Max Activating Token Index: 424