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

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

Neuron 754 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.9323. Min Act: -0.0000

Data Index: 839492 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6610. Min Act: -0.0000

Data Index: 705860 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.5573. Min Act: -0.0000

Data Index: 882209 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6595. Min Act: -0.0000

Data Index: 899099 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.5039. Min Act: -0.0000

Data Index: 892646 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.3492. Min Act: -0.0000

Data Index: 497320 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.3615. Min Act: -0.0000

Data Index: 350278 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2762. Min Act: -0.0000

Data Index: 975506 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2117. Min Act: -0.0000

Data Index: 315419 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.3002. Min Act: -0.0000

Data Index: 786351 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1152035 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2836. Min Act: -0.0000

Data Index: 602886 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.3001. Min Act: -0.0000

Data Index: 399116 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2652. Min Act: -0.0000

Data Index: 170887 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2461. Min Act: -0.0000

Data Index: 987254 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1300870 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1350498 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2049. Min Act: -0.0000

Data Index: 705356 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.1984. Min Act: -0.0000

Data Index: 224176 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.2346. Min Act: -0.0000

Data Index: 271664 (C4 (Web Text))

Max Activating Token Index: 851