Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3597 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2550. Min Act: -0.0000

Data Index: 23149 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2415. Min Act: -0.0000

Data Index: 1133471 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1318147 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2217. Min Act: -0.0000

Data Index: 511968 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2199. Min Act: -0.0000

Data Index: 703715 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2324. Min Act: -0.0000

Data Index: 61427 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2319. Min Act: -0.0000

Data Index: 84554 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2169. Min Act: -0.0000

Data Index: 576699 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2183. Min Act: -0.0000

Data Index: 878647 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1225147 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1212231 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2207. Min Act: -0.0000

Data Index: 520352 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2040. Min Act: -0.0000

Data Index: 713692 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1995. Min Act: -0.0000

Data Index: 96457 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2114. Min Act: -0.0000

Data Index: 385641 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2032. Min Act: -0.0000

Data Index: 348871 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1155091 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.2093. Min Act: -0.0000

Data Index: 703341 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1331650 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.2550. Min Range: -0.2550

Max Act: 0.1984. Min Act: -0.0000

Data Index: 206854 (C4 (Web Text))

Max Activating Token Index: 317