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

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

Neuron 3953 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8551. Min Range: -3.8551

Max Act: 3.7766. Min Act: -0.0000

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 3.8551. Min Range: -3.8551

Max Act: 3.8551. Min Act: -0.0000

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 3.8551. Min Range: -3.8551

Max Act: 3.6001. Min Act: -0.0000

Data Index: 107502 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.8551. Min Range: -3.8551

Max Act: 3.0380. Min Act: -0.0000

Data Index: 1113299 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.7930. Min Act: -0.0000

Data Index: 887281 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.6611. Min Act: -0.0000

Data Index: 521669 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.6499. Min Act: -0.0000

Data Index: 611946 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.8551. Min Range: -3.8551

Max Act: 3.0102. Min Act: -0.0000

Data Index: 1228648 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.6426. Min Act: -0.0000

Data Index: 546885 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.7341. Min Act: -0.0000

Data Index: 535181 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.6621. Min Act: -0.0000

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.7921. Min Act: -0.0000

Data Index: 462035 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.3515. Min Act: -0.0000

Data Index: 758639 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.3425. Min Act: -0.0000

Data Index: 687008 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.5546. Min Act: -0.0000

Data Index: 1185142 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.5316. Min Act: -0.0000

Data Index: 1000965 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.4073. Min Act: -0.0000

Data Index: 453515 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.2528. Min Act: -0.0000

Data Index: 299711 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.1988. Min Act: -0.0000

Data Index: 793908 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 3.8551. Min Range: -3.8551

Max Act: 2.5668. Min Act: -0.0000

Data Index: 270756 (C4 (Web Text))

Max Activating Token Index: 889