Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3046 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.5321. Min Act: -0.0001

Data Index: 1155927 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4375. Min Act: -0.0001

Data Index: 1238374 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4652. Min Act: -0.0001

Data Index: 172307 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4585. Min Act: -0.0001

Data Index: 820543 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4576. Min Act: -0.0001

Data Index: 773682 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4089. Min Act: -0.0001

Data Index: 184816 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4359. Min Act: -0.0001

Data Index: 941415 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4321. Min Act: -0.0001

Data Index: 478369 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4214. Min Act: -0.0001

Data Index: 185980 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4461. Min Act: -0.0001

Data Index: 181287 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3936. Min Act: -0.0001

Data Index: 846213 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4357. Min Act: -0.0001

Data Index: 115789 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4163. Min Act: -0.0001

Data Index: 562885 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4342. Min Act: -0.0001

Data Index: 960575 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3803. Min Act: -0.0001

Data Index: 86454 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3898. Min Act: -0.0001

Data Index: 183236 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3434. Min Act: -0.0001

Data Index: 474805 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3812. Min Act: -0.0001

Data Index: 1094116 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3638. Min Act: -0.0001

Data Index: 1099195 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3925. Min Act: -0.0001

Data Index: 452918 (C4 (Web Text))

Max Activating Token Index: 48