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

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

Neuron 1265 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1259268 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2756. Min Act: -0.0000

Data Index: 573879 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2597. Min Act: -0.0000

Data Index: 98856 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1024505 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2547. Min Act: -0.0000

Data Index: 279794 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2368. Min Act: -0.0001

Data Index: 654506 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2386. Min Act: 0.0001

Data Index: 1194738 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2339. Min Act: -0.0001

Data Index: 1193478 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1299037 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2368. Min Act: -0.0001

Data Index: 401268 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1184821 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1250018 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1118846 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2141. Min Act: -0.0000

Data Index: 318684 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2148. Min Act: -0.0000

Data Index: 648476 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1248066 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1252898 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1317739 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.2119. Min Act: -0.0000

Data Index: 596142 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.3030. Min Range: -0.3030

Max Act: 0.1939. Min Act: -0.0000

Data Index: 555070 (C4 (Web Text))

Max Activating Token Index: 150