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

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

Neuron 4477 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1024646 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2768. Min Act: -0.0000

Data Index: 149847 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2571. Min Act: -0.0000

Data Index: 431664 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1186266 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1150297 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2506. Min Act: -0.0000

Data Index: 103154 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2399. Min Act: -0.0000

Data Index: 753904 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2432. Min Act: -0.0000

Data Index: 245563 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1145308 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1039738 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2205. Min Act: -0.0000

Data Index: 864182 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2224. Min Act: -0.0000

Data Index: 174112 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2059. Min Act: -0.0000

Data Index: 565444 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2050. Min Act: -0.0000

Data Index: 363697 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2104. Min Act: -0.0000

Data Index: 824129 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1931. Min Act: -0.0000

Data Index: 5414 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2056. Min Act: -0.0000

Data Index: 988049 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2044. Min Act: -0.0000

Data Index: 211769 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1197172 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.2922. Min Range: -0.2922

Max Act: 0.2130. Min Act: -0.0000

Data Index: 971883 (C4 (Web Text))

Max Activating Token Index: 232