Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2294 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1196. Min Act: -0.0001

Data Index: 361551 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1133822 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1241. Min Act: -0.0002

Data Index: 630276 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1232. Min Act: -0.0001

Data Index: 316504 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1186. Min Act: -0.0002

Data Index: 529098 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1105. Min Act: -0.0001

Data Index: 872299 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1154. Min Act: -0.0002

Data Index: 575043 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1094310 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1117260 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1123. Min Act: -0.0001

Data Index: 927379 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1244998 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1141. Min Act: -0.0001

Data Index: 370493 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1019. Min Act: -0.0002

Data Index: 135515 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1080120 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1232453 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1070. Min Act: -0.0002

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1119. Min Act: -0.0002

Data Index: 370841 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1296987 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1058. Min Act: -0.0002

Data Index: 250497 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.1273. Min Range: -0.1273

Max Act: 0.1052. Min Act: -0.0002

Data Index: 568964 (C4 (Web Text))

Max Activating Token Index: 350