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

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

Neuron 3858 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.3123. Min Act: -0.0001

Data Index: 498083 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2745. Min Act: -0.0001

Data Index: 819083 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2799. Min Act: -0.0001

Data Index: 361617 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2795. Min Act: -0.0001

Data Index: 610993 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2893. Min Act: -0.0001

Data Index: 1075096 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2640. Min Act: -0.0001

Data Index: 426474 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2533. Min Act: -0.0001

Data Index: 9243 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2594. Min Act: -0.0001

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2408. Min Act: -0.0001

Data Index: 715847 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2602. Min Act: -0.0001

Data Index: 356328 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2304. Min Act: -0.0001

Data Index: 690226 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2365. Min Act: -0.0001

Data Index: 527780 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2295. Min Act: -0.0001

Data Index: 213148 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2270. Min Act: -0.0001

Data Index: 198548 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2396. Min Act: -0.0001

Data Index: 865127 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2281. Min Act: -0.0001

Data Index: 730855 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2463. Min Act: -0.0001

Data Index: 433766 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1005227 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2343. Min Act: -0.0001

Data Index: 573298 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.3123. Min Range: -0.3123

Max Act: 0.2164. Min Act: -0.0001

Data Index: 862384 (C4 (Web Text))

Max Activating Token Index: 548