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

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

Neuron 4987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1258889 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.1731. Min Act: -0.0000

Data Index: 1143700 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0490. Min Act: -0.0000

Data Index: 627178 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9658. Min Act: -0.0000

Data Index: 854815 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0126. Min Act: -0.0000

Data Index: 611550 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.2792. Min Range: -1.2792

Max Act: 1.0553. Min Act: -0.0000

Data Index: 914704 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1119323 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9307. Min Act: -0.0000

Data Index: 787135 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1199858 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9416. Min Act: -0.0000

Data Index: 531775 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1107126 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1265153 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.9053. Min Act: -0.0000

Data Index: 429792 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8846. Min Act: -0.0000

Data Index: 310505 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8692. Min Act: -0.0000

Data Index: 439875 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8890. Min Act: -0.0000

Data Index: 489747 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1149972 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8633. Min Act: -0.0000

Data Index: 740661 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.7773. Min Act: -0.0000

Data Index: 573089 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.2792. Min Range: -1.2792

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1039717 (C4 (Web Text))

Max Activating Token Index: 534