Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0005

Data Index: 689869 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1243. Min Act: -0.0005

Data Index: 58573 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1167. Min Act: -0.0005

Data Index: 1178620 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1158. Min Act: -0.0005

Data Index: 907072 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1139. Min Act: -0.0005

Data Index: 1359261 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1130. Min Act: -0.0005

Data Index: 495255 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1083. Min Act: -0.0005

Data Index: 539722 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1097. Min Act: -0.0005

Data Index: 437240 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1159. Min Act: -0.0005

Data Index: 560944 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1135. Min Act: -0.0005

Data Index: 798327 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1116. Min Act: -0.0005

Data Index: 651170 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1158. Min Act: -0.0005

Data Index: 355963 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1130. Min Act: -0.0005

Data Index: 1127931 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1110. Min Act: -0.0005

Data Index: 404541 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1131. Min Act: -0.0005

Data Index: 39439 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1086. Min Act: -0.0005

Data Index: 1201637 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1159. Min Act: -0.0005

Data Index: 830562 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1092. Min Act: -0.0005

Data Index: 1340870 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1109. Min Act: -0.0005

Data Index: 909205 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1079. Min Act: -0.0005

Data Index: 769419 (C4 (Web Text))

Max Activating Token Index: 735