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

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

Neuron 1999 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: 1.7273. Min Range: -1.7273

Max Act: 1.7273. Min Act: -0.0001

Data Index: 872621 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.5138. Min Act: -0.0001

Data Index: 544470 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.5853. Min Act: -0.0001

Data Index: 279517 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.5127. Min Act: -0.0001

Data Index: 1297151 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.3368. Min Act: -0.0001

Data Index: 780776 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.3672. Min Act: -0.0001

Data Index: 1288459 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.3413. Min Act: -0.0001

Data Index: 910976 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.3567. Min Act: -0.0001

Data Index: 214592 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.3167. Min Act: -0.0001

Data Index: 136327 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.2585. Min Act: -0.0001

Data Index: 1215873 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.2945. Min Act: -0.0001

Data Index: 365342 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.1925. Min Act: -0.0001

Data Index: 192308 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.0994. Min Act: -0.0001

Data Index: 1301103 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.0881. Min Act: -0.0001

Data Index: 483743 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.0541. Min Act: -0.0001

Data Index: 121712 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.1937. Min Act: -0.0001

Data Index: 359062 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.0848. Min Act: -0.0001

Data Index: 911483 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.0064. Min Act: -0.0001

Data Index: 281441 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.0581. Min Act: -0.0001

Data Index: 138029 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 1.7273. Min Range: -1.7273

Max Act: 1.0591. Min Act: -0.0001

Data Index: 188535 (C4 (Web Text))

Max Activating Token Index: 288