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

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

Neuron 4464 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3998. Min Range: -3.3998

Max Act: 3.3998. Min Act: -0.0000

Data Index: 1107517 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.2723. Min Act: -0.0000

Data Index: 829872 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.5399. Min Act: -0.0000

Data Index: 952536 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.4436. Min Act: -0.0000

Data Index: 71457 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.1673. Min Act: -0.0000

Data Index: 1024693 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.3697. Min Act: -0.0000

Data Index: 171990 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.1345. Min Act: -0.0000

Data Index: 658829 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.3490. Min Act: -0.0000

Data Index: 858390 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.3363. Min Act: -0.0000

Data Index: 223461 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.5658. Min Act: -0.0000

Data Index: 349098 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.2217. Min Act: -0.0000

Data Index: 631064 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.4465. Min Act: -0.0000

Data Index: 1042093 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.4070. Min Act: -0.0000

Data Index: 1107874 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.1665. Min Act: -0.0000

Data Index: 564589 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.2548. Min Act: -0.0000

Data Index: 515225 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.6100. Min Act: -0.0000

Data Index: 200408 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.4629. Min Act: -0.0000

Data Index: 1198091 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.3332. Min Act: -0.0000

Data Index: 939520 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.4364. Min Act: -0.0000

Data Index: 1223848 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.3998. Min Range: -3.3998

Max Act: 2.3213. Min Act: -0.0000

Data Index: 638560 (C4 (Web Text))

Max Activating Token Index: 307