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

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

Neuron 1522 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6942. Min Act: -0.0000

Data Index: 561134 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1134713 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6367. Min Act: -0.0000

Data Index: 507373 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6523. Min Act: -0.0000

Data Index: 580700 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5948. Min Act: -0.0000

Data Index: 829583 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6137. Min Act: -0.0000

Data Index: 181432 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5736. Min Act: -0.0000

Data Index: 874893 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5881. Min Act: -0.0000

Data Index: 591735 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5793. Min Act: -0.0000

Data Index: 933821 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1049747 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5801. Min Act: -0.0000

Data Index: 39964 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5603. Min Act: -0.0000

Data Index: 981711 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5353. Min Act: -0.0000

Data Index: 192741 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5123. Min Act: -0.0000

Data Index: 930443 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5493. Min Act: -0.0000

Data Index: 959013 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5266. Min Act: -0.0000

Data Index: 460178 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1237660 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5396. Min Act: -0.0000

Data Index: 952893 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5053. Min Act: -0.0000

Data Index: 463238 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5568. Min Act: -0.0000

Data Index: 966564 (C4 (Web Text))

Max Activating Token Index: 595