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

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

Neuron 6036 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: 2.1977. Min Range: -2.1977

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1308096 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.9947. Min Act: -0.0000

Data Index: 44719 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.9657. Min Act: -0.0000

Data Index: 1209776 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.7300. Min Act: -0.0000

Data Index: 649326 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.8263. Min Act: -0.0000

Data Index: 870054 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.8433. Min Act: -0.0000

Data Index: 812610 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.7488. Min Act: -0.0000

Data Index: 1038057 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.8201. Min Act: -0.0000

Data Index: 482923 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1234003 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.6571. Min Act: -0.0000

Data Index: 251 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.5256. Min Act: -0.0000

Data Index: 295073 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.6567. Min Act: -0.0000

Data Index: 545974 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.5160. Min Act: -0.0000

Data Index: 997486 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.4988. Min Act: -0.0000

Data Index: 657400 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1037201 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.4829. Min Act: -0.0000

Data Index: 904490 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.5527. Min Act: -0.0000

Data Index: 748902 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.3501. Min Act: -0.0000

Data Index: 945847 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.4328. Min Act: -0.0000

Data Index: 89137 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 2.1977. Min Range: -2.1977

Max Act: 1.2977. Min Act: -0.0000

Data Index: 756236 (C4 (Web Text))

Max Activating Token Index: 187