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

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

Neuron 4625 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: 1.9080. Min Range: -1.9080

Max Act: 1.8288. Min Act: -0.0000

Data Index: 159198 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.8288. Min Act: -0.0000

Data Index: 123676 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.9080. Min Act: -0.0000

Data Index: 843258 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.6239. Min Act: -0.0000

Data Index: 612110 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.4962. Min Act: -0.0000

Data Index: 280949 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.4765. Min Act: -0.0000

Data Index: 228867 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.3644. Min Act: -0.0000

Data Index: 976005 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.4142. Min Act: -0.0000

Data Index: 597012 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2385. Min Act: -0.0000

Data Index: 107043 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2553. Min Act: -0.0000

Data Index: 120727 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2366. Min Act: -0.0000

Data Index: 378975 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1925. Min Act: -0.0000

Data Index: 636409 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2518. Min Act: -0.0000

Data Index: 164411 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1978. Min Act: -0.0000

Data Index: 1159625 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1050268 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1631. Min Act: -0.0000

Data Index: 23617 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1549. Min Act: -0.0000

Data Index: 438289 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1713. Min Act: -0.0000

Data Index: 293598 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1106194 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1381. Min Act: -0.0000

Data Index: 251710 (C4 (Web Text))

Max Activating Token Index: 560