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

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

Neuron 1011 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2599. Min Act: -0.0004

Data Index: 409405 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2643. Min Act: -0.0004

Data Index: 512469 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2638. Min Act: -0.0004

Data Index: 1118554 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2369. Min Act: -0.0004

Data Index: 1288832 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2616. Min Act: -0.0004

Data Index: 37513 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2290. Min Act: -0.0004

Data Index: 503654 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2157. Min Act: -0.0004

Data Index: 638379 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2285. Min Act: -0.0004

Data Index: 528057 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2008. Min Act: -0.0004

Data Index: 106411 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2175. Min Act: -0.0004

Data Index: 315111 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2254. Min Act: -0.0004

Data Index: 332901 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2238. Min Act: -0.0004

Data Index: 753917 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2221. Min Act: -0.0004

Data Index: 625205 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2122. Min Act: -0.0004

Data Index: 633040 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1979. Min Act: -0.0004

Data Index: 935921 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2604. Min Act: -0.0004

Data Index: 1047104 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2190. Min Act: -0.0004

Data Index: 807893 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2181. Min Act: -0.0004

Data Index: 377499 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.2165. Min Act: -0.0004

Data Index: 1122474 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.2643. Min Range: -0.2643

Max Act: 0.1891. Min Act: -0.0004

Data Index: 557194 (C4 (Web Text))

Max Activating Token Index: 619