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

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

Neuron 4180 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.7539. Min Act: -0.0002

Data Index: 490069 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.6124. Min Act: -0.0003

Data Index: 930468 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.6370. Min Act: -0.0002

Data Index: 1303646 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.5188. Min Act: -0.0002

Data Index: 777960 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4682. Min Act: -0.0002

Data Index: 290010 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4573. Min Act: -0.0002

Data Index: 672303 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4363. Min Act: -0.0002

Data Index: 262566 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4373. Min Act: -0.0002

Data Index: 66418 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4236. Min Act: -0.0003

Data Index: 856276 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3933. Min Act: -0.0003

Data Index: 555555 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.4069. Min Act: -0.0002

Data Index: 461017 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3730. Min Act: -0.0002

Data Index: 71340 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3972. Min Act: -0.0002

Data Index: 104464 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3754. Min Act: -0.0002

Data Index: 1122767 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3950. Min Act: -0.0002

Data Index: 607533 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3731. Min Act: -0.0002

Data Index: 421967 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3586. Min Act: -0.0002

Data Index: 668788 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3595. Min Act: -0.0003

Data Index: 477086 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3516. Min Act: -0.0002

Data Index: 1335734 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 1.7539. Min Range: -1.7539

Max Act: 1.3985. Min Act: -0.0002

Data Index: 1103687 (C4 (Web Text))

Max Activating Token Index: 857