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

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

Neuron 5119 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: 2.2635. Min Range: -2.2635

Max Act: 2.2635. Min Act: -0.0000

Data Index: 1203236 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 2.2635. Min Range: -2.2635

Max Act: 2.2444. Min Act: -0.0000

Data Index: 1098681 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 2.2635. Min Range: -2.2635

Max Act: 2.1936. Min Act: -0.0000

Data Index: 904783 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 2.2635. Min Range: -2.2635

Max Act: 2.0294. Min Act: -0.0000

Data Index: 1150565 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 2.2635. Min Range: -2.2635

Max Act: 2.0259. Min Act: -0.0000

Data Index: 392609 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.9033. Min Act: -0.0000

Data Index: 1316668 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.9157. Min Act: -0.0000

Data Index: 499017 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.9087. Min Act: -0.0000

Data Index: 992521 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.8857. Min Act: -0.0000

Data Index: 42115 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.8932. Min Act: -0.0000

Data Index: 1230463 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.8381. Min Act: -0.0000

Data Index: 888131 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.7941. Min Act: -0.0000

Data Index: 933145 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.8709. Min Act: -0.0000

Data Index: 771762 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.7610. Min Act: -0.0000

Data Index: 1189823 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.6638. Min Act: -0.0000

Data Index: 306275 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.6527. Min Act: -0.0000

Data Index: 439393 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1114656 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.7104. Min Act: -0.0000

Data Index: 326611 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.5897. Min Act: -0.0000

Data Index: 451490 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 2.2635. Min Range: -2.2635

Max Act: 1.7547. Min Act: -0.0000

Data Index: 1188007 (C4 (Web Text))

Max Activating Token Index: 364