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

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

Neuron 1377 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1367643 (Python Code)

Max Activating Token Index: 210

Text #1

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.8191. Min Act: -0.0000

Data Index: 889133 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.7071. Min Act: -0.0000

Data Index: 112694 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6352. Min Act: -0.0000

Data Index: 950463 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6820. Min Act: -0.0000

Data Index: 506245 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1004016 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6724. Min Act: -0.0001

Data Index: 707127 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1006752 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6573. Min Act: -0.0000

Data Index: 435061 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6870. Min Act: -0.0000

Data Index: 663883 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6699. Min Act: -0.0000

Data Index: 713036 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6272. Min Act: -0.0000

Data Index: 689038 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6077. Min Act: -0.0000

Data Index: 880237 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.5985. Min Act: -0.0000

Data Index: 106422 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6561. Min Act: -0.0000

Data Index: 1196632 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1216729 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1335469 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.5586. Min Act: -0.0000

Data Index: 967389 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.5590. Min Act: -0.0000

Data Index: 374607 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.8191. Min Range: -0.8191

Max Act: 0.5758. Min Act: -0.0000

Data Index: 1633634 (Python Code)

Max Activating Token Index: 656