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

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

Neuron 2323 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: 0.1335. Min Range: -0.1335

Max Act: 0.1317. Min Act: -0.0001

Data Index: 811626 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1259. Min Act: -0.0001

Data Index: 293852 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1335. Min Act: -0.0001

Data Index: 177050 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1022038 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1058906 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1173. Min Act: -0.0000

Data Index: 13555 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1178. Min Act: -0.0001

Data Index: 195685 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1163. Min Act: -0.0000

Data Index: 788525 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1120. Min Act: -0.0001

Data Index: 112750 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1197. Min Act: -0.0000

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1063. Min Act: -0.0000

Data Index: 473290 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1128. Min Act: -0.0000

Data Index: 1553030 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1051. Min Act: -0.0000

Data Index: 113838 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1220370 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1058. Min Act: -0.0000

Data Index: 483966 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1277046 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1081. Min Act: -0.0000

Data Index: 388735 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1072. Min Act: -0.0001

Data Index: 1109129 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1245583 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.1335. Min Range: -0.1335

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1215849 (C4 (Web Text))

Max Activating Token Index: 270