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

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

Neuron 339 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: 0.0203. Min Range: -0.0203

Max Act: 0.0203. Min Act: -0.0006

Data Index: 746716 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0200. Min Act: -0.0006

Data Index: 127102 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0192. Min Act: -0.0006

Data Index: 673982 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0173. Min Act: -0.0006

Data Index: 501509 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0166. Min Act: -0.0006

Data Index: 315943 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1231663 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0164. Min Act: -0.0006

Data Index: 107517 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0161. Min Act: -0.0006

Data Index: 262762 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1425184 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0160. Min Act: -0.0005

Data Index: 1601928 (Python Code)

Max Activating Token Index: 982

Text #10

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0157. Min Act: -0.0006

Data Index: 272655 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1041594 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1449066 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0152. Min Act: -0.0005

Data Index: 1430257 (Python Code)

Max Activating Token Index: 889

Text #14

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0152. Min Act: -0.0006

Data Index: 33017 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0155. Min Act: -0.0006

Data Index: 553219 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0151. Min Act: -0.0006

Data Index: 822154 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1292751 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1446139 (Python Code)

Max Activating Token Index: 384

Text #19

Max Range: 0.0203. Min Range: -0.0203

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1359568 (C4 (Web Text))

Max Activating Token Index: 5