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

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

Neuron 2080 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1121337 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.6007. Min Act: -0.0000

Data Index: 792634 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1040403 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.5127. Min Act: -0.0000

Data Index: 938262 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.5861. Min Act: -0.0000

Data Index: 243502 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.5196. Min Act: -0.0000

Data Index: 801016 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4417. Min Act: -0.0000

Data Index: 346813 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.5011. Min Act: -0.0000

Data Index: 868095 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.5085. Min Act: -0.0000

Data Index: 876451 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4554. Min Act: -0.0000

Data Index: 718240 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4678. Min Act: -0.0000

Data Index: 97269 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4573. Min Act: -0.0000

Data Index: 20555 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4404. Min Act: -0.0000

Data Index: 481174 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4743. Min Act: -0.0000

Data Index: 428094 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1261814 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1650508 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4557. Min Act: -0.0000

Data Index: 786750 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4333. Min Act: -0.0000

Data Index: 368895 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4157. Min Act: -0.0000

Data Index: 662253 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4272. Min Act: -0.0000

Data Index: 968468 (C4 (Web Text))

Max Activating Token Index: 612