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

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

Neuron 555 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2770. Min Range: -2.2770

Max Act: 2.1630. Min Act: -0.0001

Data Index: 567009 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 2.2770. Min Range: -2.2770

Max Act: 2.1574. Min Act: -0.0000

Data Index: 789020 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 2.2770. Min Range: -2.2770

Max Act: 2.2770. Min Act: -0.0000

Data Index: 374568 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 2.2770. Min Range: -2.2770

Max Act: 2.0638. Min Act: -0.0001

Data Index: 167041 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.9337. Min Act: -0.0000

Data Index: 635207 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.8152. Min Act: -0.0000

Data Index: 485942 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7521. Min Act: -0.0000

Data Index: 266305 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.8192. Min Act: -0.0000

Data Index: 533357 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.8029. Min Act: -0.0000

Data Index: 137578 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7094. Min Act: -0.0001

Data Index: 596248 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.8973. Min Act: -0.0000

Data Index: 827474 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7707. Min Act: -0.0000

Data Index: 838711 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7662. Min Act: -0.0001

Data Index: 1446304 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7576. Min Act: -0.0001

Data Index: 591206 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7327. Min Act: -0.0001

Data Index: 855776 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7116. Min Act: -0.0000

Data Index: 1226844 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7002. Min Act: -0.0001

Data Index: 1083602 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.7822. Min Act: -0.0000

Data Index: 124246 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.6815. Min Act: -0.0000

Data Index: 1044466 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 2.2770. Min Range: -2.2770

Max Act: 1.6618. Min Act: -0.0001

Data Index: 1407376 (Python Code)

Max Activating Token Index: 804