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

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

Neuron 4282 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: 1.8386. Min Range: -1.8386

Max Act: 1.8386. Min Act: -0.0000

Data Index: 12999 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.7698. Min Act: -0.0000

Data Index: 1194465 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.6037. Min Act: -0.0000

Data Index: 764787 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.5006. Min Act: -0.0000

Data Index: 698870 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4060. Min Act: -0.0000

Data Index: 621578 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.4533. Min Act: -0.0000

Data Index: 398740 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3647. Min Act: -0.0000

Data Index: 375371 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3596. Min Act: -0.0000

Data Index: 465886 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2921. Min Act: -0.0000

Data Index: 970706 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2729. Min Act: -0.0000

Data Index: 790772 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3747. Min Act: -0.0000

Data Index: 1100257 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2829. Min Act: -0.0000

Data Index: 663983 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2722. Min Act: -0.0000

Data Index: 255407 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3347. Min Act: -0.0000

Data Index: 352772 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3351. Min Act: -0.0000

Data Index: 113678 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3167. Min Act: -0.0000

Data Index: 351034 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2657. Min Act: -0.0000

Data Index: 691919 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3033. Min Act: -0.0000

Data Index: 506013 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.2559. Min Act: -0.0000

Data Index: 314426 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.8386. Min Range: -1.8386

Max Act: 1.3233. Min Act: -0.0000

Data Index: 463401 (C4 (Web Text))

Max Activating Token Index: 468