Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 764 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0204. Min Act: -0.0006

Data Index: 652919 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0190. Min Act: -0.0006

Data Index: 318210 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0186. Min Act: -0.0006

Data Index: 921787 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0182. Min Act: -0.0005

Data Index: 238627 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0179. Min Act: -0.0005

Data Index: 269127 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0179. Min Act: -0.0006

Data Index: 803153 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0156. Min Act: -0.0006

Data Index: 1296106 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0156. Min Act: -0.0005

Data Index: 152956 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0153. Min Act: -0.0006

Data Index: 12418 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1155679 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0144. Min Act: -0.0006

Data Index: 67242 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0144. Min Act: -0.0005

Data Index: 215995 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0141. Min Act: -0.0006

Data Index: 1734 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1006326 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0144. Min Act: -0.0006

Data Index: 896084 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0145. Min Act: -0.0006

Data Index: 607314 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0143. Min Act: -0.0006

Data Index: 518517 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0142. Min Act: -0.0006

Data Index: 786223 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0141. Min Act: -0.0006

Data Index: 733596 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.0204. Min Range: -0.0204

Max Act: 0.0141. Min Act: -0.0005

Data Index: 967451 (C4 (Web Text))

Max Activating Token Index: 906