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

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

Neuron 6087 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0304. Min Range: -1.0304

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1085133 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1245628 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.8075. Min Act: -0.0000

Data Index: 512433 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.7414. Min Act: -0.0000

Data Index: 6595 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.5643. Min Act: -0.0000

Data Index: 115717 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.6128. Min Act: -0.0000

Data Index: 839662 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.5863. Min Act: -0.0000

Data Index: 99867 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.5466. Min Act: -0.0000

Data Index: 70508 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.4860. Min Act: -0.0000

Data Index: 409405 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.4908. Min Act: -0.0000

Data Index: 512469 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1252959 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1312590 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.4726. Min Act: -0.0000

Data Index: 520747 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.3866. Min Act: -0.0000

Data Index: 110897 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1054699 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.4208. Min Act: -0.0000

Data Index: 13555 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.3966. Min Act: -0.0000

Data Index: 688467 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.3603. Min Act: -0.0000

Data Index: 293852 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.3933. Min Act: -0.0000

Data Index: 177050 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 1.0304. Min Range: -1.0304

Max Act: 0.3967. Min Act: -0.0000

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 368