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

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

Neuron 2620 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.7621. Min Act: -0.0000

Data Index: 633020 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.7542. Min Act: -0.0000

Data Index: 909141 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.5597. Min Act: -0.0000

Data Index: 397058 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.2585. Min Act: -0.0000

Data Index: 1197201 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.0726. Min Act: -0.0000

Data Index: 478113 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.1272. Min Act: -0.0000

Data Index: 205344 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.2604. Min Act: -0.0000

Data Index: 530232 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 6.7621. Min Range: -6.7621

Max Act: 6.0144. Min Act: -0.0000

Data Index: 796797 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.9598. Min Act: -0.0000

Data Index: 1259484 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.8751. Min Act: -0.0000

Data Index: 627661 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.6632. Min Act: -0.0000

Data Index: 563476 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.4483. Min Act: -0.0000

Data Index: 742764 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.6104. Min Act: -0.0000

Data Index: 965051 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.3832. Min Act: -0.0000

Data Index: 1052212 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.5418. Min Act: -0.0000

Data Index: 1036339 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.3066. Min Act: -0.0000

Data Index: 1226608 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.5004. Min Act: -0.0000

Data Index: 568288 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.6633. Min Act: -0.0000

Data Index: 111146 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.2633. Min Act: -0.0000

Data Index: 144129 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 6.7621. Min Range: -6.7621

Max Act: 5.7734. Min Act: -0.0000

Data Index: 1307219 (C4 (Web Text))

Max Activating Token Index: 370