Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1061 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.9506. Min Act: -0.0001

Data Index: 22361 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.7686. Min Act: -0.0001

Data Index: 9425 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.6970. Min Act: -0.0001

Data Index: 178858 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.7827. Min Act: -0.0001

Data Index: 671720 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.7227. Min Act: -0.0001

Data Index: 766492 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 4.0313. Min Range: -4.0313

Max Act: 4.0313. Min Act: -0.0001

Data Index: 173717 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.3386. Min Act: -0.0001

Data Index: 119489 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.4951. Min Act: -0.0001

Data Index: 1022452 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.5897. Min Act: -0.0001

Data Index: 224481 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.5424. Min Act: -0.0001

Data Index: 24546 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.5329. Min Act: -0.0001

Data Index: 982060 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.5418. Min Act: -0.0001

Data Index: 1355581 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.4948. Min Act: -0.0001

Data Index: 8887 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.4751. Min Act: -0.0001

Data Index: 417703 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.3204. Min Act: -0.0001

Data Index: 239287 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.3147. Min Act: -0.0001

Data Index: 1075462 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.4568. Min Act: -0.0001

Data Index: 424266 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.4578. Min Act: -0.0001

Data Index: 479280 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.3021. Min Act: -0.0001

Data Index: 279949 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 4.0313. Min Range: -4.0313

Max Act: 3.2992. Min Act: -0.0001

Data Index: 727630 (C4 (Web Text))

Max Activating Token Index: 19