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

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

Neuron 2839 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.2493. Min Range: -8.2493

Max Act: 8.2493. Min Act: -0.0000

Data Index: 780411 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 8.2493. Min Range: -8.2493

Max Act: 7.8428. Min Act: -0.0000

Data Index: 662697 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 8.2493. Min Range: -8.2493

Max Act: 7.3172. Min Act: -0.0000

Data Index: 79225 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.8385. Min Act: -0.0000

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.8982. Min Act: -0.0000

Data Index: 580923 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.5796. Min Act: -0.0000

Data Index: 343667 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.5328. Min Act: -0.0000

Data Index: 340361 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.6101. Min Act: -0.0000

Data Index: 837391 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.3336. Min Act: -0.0000

Data Index: 621713 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.0707. Min Act: -0.0000

Data Index: 885963 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.2693. Min Act: -0.0000

Data Index: 504874 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.0640. Min Act: -0.0000

Data Index: 542430 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.0619. Min Act: -0.0000

Data Index: 165895 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 8.2493. Min Range: -8.2493

Max Act: 5.8182. Min Act: -0.0000

Data Index: 1203591 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 8.2493. Min Range: -8.2493

Max Act: 6.0104. Min Act: -0.0000

Data Index: 1119098 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 8.2493. Min Range: -8.2493

Max Act: 5.9908. Min Act: -0.0000

Data Index: 934991 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 8.2493. Min Range: -8.2493

Max Act: 5.7889. Min Act: -0.0000

Data Index: 1010865 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 8.2493. Min Range: -8.2493

Max Act: 5.7759. Min Act: -0.0000

Data Index: 1305064 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 8.2493. Min Range: -8.2493

Max Act: 5.7472. Min Act: -0.0000

Data Index: 885864 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 8.2493. Min Range: -8.2493

Max Act: 5.7488. Min Act: -0.0000

Data Index: 690599 (C4 (Web Text))

Max Activating Token Index: 266