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

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

Neuron 917 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.3853. Min Act: -0.0000

Data Index: 450740 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1070653 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.2340. Min Act: -0.0000

Data Index: 753961 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.2238. Min Act: -0.0000

Data Index: 903256 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1309. Min Act: -0.0000

Data Index: 115272 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1486. Min Act: -0.0000

Data Index: 335429 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1270. Min Act: -0.0000

Data Index: 706440 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0914. Min Act: -0.0000

Data Index: 1196899 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1459. Min Act: -0.0000

Data Index: 905868 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1588431 (Python Code)

Max Activating Token Index: 646

Text #10

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0072. Min Act: -0.0000

Data Index: 141169 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1340539 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0647. Min Act: -0.0000

Data Index: 197353 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0543. Min Act: -0.0000

Data Index: 893199 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0950. Min Act: -0.0000

Data Index: 857894 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1078584 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.3853. Min Range: -1.3853

Max Act: 1.0326. Min Act: -0.0000

Data Index: 540958 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.9558. Min Act: -0.0000

Data Index: 932610 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.9823. Min Act: -0.0000

Data Index: 413059 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 1.3853. Min Range: -1.3853

Max Act: 0.9518. Min Act: -0.0000

Data Index: 789923 (C4 (Web Text))

Max Activating Token Index: 228