Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2192 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0001

Data Index: 216292 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1483. Min Act: -0.0001

Data Index: 269346 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1355. Min Act: -0.0001

Data Index: 133511 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1268276 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1298. Min Act: -0.0001

Data Index: 412622 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1224. Min Act: -0.0001

Data Index: 178849 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1111. Min Act: -0.0001

Data Index: 563159 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1209. Min Act: -0.0001

Data Index: 575399 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1190. Min Act: -0.0001

Data Index: 739730 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1203. Min Act: -0.0001

Data Index: 447956 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1052701 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1158. Min Act: -0.0001

Data Index: 716229 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1155. Min Act: -0.0001

Data Index: 157254 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1147. Min Act: -0.0001

Data Index: 348898 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1137. Min Act: -0.0001

Data Index: 203808 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1254. Min Act: -0.0001

Data Index: 801818 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1049. Min Act: -0.0001

Data Index: 773114 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1006906 (C4 (Web Text))

Max Activating Token Index: 181

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1129. Min Act: -0.0001

Data Index: 62047 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1223113 (C4 (Web Text))

Max Activating Token Index: 213