Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 302 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0547. Min Range: -2.0547

Max Act: 2.0547. Min Act: -0.0000

Data Index: 1129285 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.6680. Min Act: -0.0000

Data Index: 815043 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.5769. Min Act: -0.0000

Data Index: 1181727 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.4766. Min Act: -0.0000

Data Index: 39309 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.4211. Min Act: -0.0000

Data Index: 1082602 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1017282 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.3528. Min Act: -0.0000

Data Index: 591923 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.3361. Min Act: -0.0000

Data Index: 584888 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1201096 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2696. Min Act: -0.0000

Data Index: 633602 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.3300. Min Act: 0.0000

Data Index: 1337378 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.3323. Min Act: -0.0000

Data Index: 1079623 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2060. Min Act: -0.0000

Data Index: 1143246 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2240. Min Act: -0.0000

Data Index: 598424 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2265. Min Act: -0.0000

Data Index: 341263 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2673. Min Act: -0.0000

Data Index: 302273 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2145. Min Act: -0.0000

Data Index: 313089 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2038. Min Act: -0.0000

Data Index: 256013 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2103. Min Act: 0.0000

Data Index: 118390 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 2.0547. Min Range: -2.0547

Max Act: 1.2760. Min Act: -0.0000

Data Index: 1355998 (C4 (Web Text))

Max Activating Token Index: 343