Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1972 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1554. Min Act: -0.0001

Data Index: 876642 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1466. Min Act: -0.0001

Data Index: 629041 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1172825 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1293. Min Act: -0.0001

Data Index: 436759 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1128. Min Act: -0.0001

Data Index: 173655 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1219160 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1080200 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1197. Min Act: -0.0001

Data Index: 543277 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1228. Min Act: -0.0001

Data Index: 218872 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1138. Min Act: -0.0001

Data Index: 5872 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1130. Min Act: -0.0001

Data Index: 98178 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1165. Min Act: -0.0001

Data Index: 862742 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1240. Min Act: -0.0001

Data Index: 562760 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1102235 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1153. Min Act: -0.0001

Data Index: 812406 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1108. Min Act: -0.0001

Data Index: 974095 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1140. Min Act: -0.0001

Data Index: 1063348 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1102. Min Act: -0.0001

Data Index: 596876 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1232452 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.1554. Min Range: -0.1554

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1152973 (C4 (Web Text))

Max Activating Token Index: 437