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

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

Neuron 1456 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1264505 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1003281 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1285. Min Act: -0.0001

Data Index: 707680 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1283. Min Act: -0.0001

Data Index: 246706 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1168. Min Act: -0.0001

Data Index: 586254 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1244. Min Act: -0.0002

Data Index: 223864 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1282. Min Act: -0.0001

Data Index: 182156 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1112148 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1159. Min Act: -0.0001

Data Index: 20405 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1104. Min Act: -0.0001

Data Index: 444203 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1084. Min Act: -0.0001

Data Index: 898237 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1223520 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1010954 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1046. Min Act: -0.0001

Data Index: 537161 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1111. Min Act: -0.0001

Data Index: 607212 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0938. Min Act: -0.0001

Data Index: 141099 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.0996. Min Act: -0.0001

Data Index: 762634 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1232885 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1053. Min Act: -0.0001

Data Index: 542684 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.1597. Min Range: -0.1597

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1247652 (C4 (Web Text))

Max Activating Token Index: 624