Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1570 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2152. Min Range: -2.2152

Max Act: 2.2152. Min Act: -0.0000

Data Index: 56917 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 2.2152. Min Range: -2.2152

Max Act: 2.1195. Min Act: -0.0001

Data Index: 746033 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.7905. Min Act: -0.0000

Data Index: 303078 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.9574. Min Act: -0.0000

Data Index: 1161665 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.9623. Min Act: -0.0001

Data Index: 946680 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 2.2152. Min Range: -2.2152

Max Act: 2.0192. Min Act: -0.0000

Data Index: 244851 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.9092. Min Act: -0.0000

Data Index: 223270 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8901. Min Act: -0.0001

Data Index: 495699 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.9937. Min Act: -0.0000

Data Index: 1214435 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.6882. Min Act: -0.0001

Data Index: 1305574 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8845. Min Act: -0.0001

Data Index: 787956 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8428. Min Act: -0.0000

Data Index: 1078231 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8306. Min Act: -0.0000

Data Index: 1105698 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8163. Min Act: -0.0000

Data Index: 1184139 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8185. Min Act: -0.0000

Data Index: 757133 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8943. Min Act: -0.0000

Data Index: 893368 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.7126. Min Act: -0.0001

Data Index: 1122189 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8055. Min Act: -0.0001

Data Index: 653837 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.8935. Min Act: -0.0001

Data Index: 1006802 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 2.2152. Min Range: -2.2152

Max Act: 1.6798. Min Act: -0.0000

Data Index: 449964 (C4 (Web Text))

Max Activating Token Index: 973