Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6882. Min Act: -0.0001

Data Index: 1253107 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6179. Min Act: -0.0001

Data Index: 133845 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5469. Min Act: -0.0001

Data Index: 224031 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5662. Min Act: -0.0001

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5842. Min Act: -0.0000

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.6111. Min Act: -0.0001

Data Index: 1295470 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5289. Min Act: -0.0001

Data Index: 74804 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4664. Min Act: -0.0001

Data Index: 243406 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.5170. Min Act: -0.0001

Data Index: 953352 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4137. Min Act: -0.0001

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4738. Min Act: -0.0001

Data Index: 46588 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4831. Min Act: -0.0001

Data Index: 433850 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4870. Min Act: -0.0001

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4471. Min Act: -0.0001

Data Index: 824168 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4332. Min Act: -0.0001

Data Index: 455802 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4493. Min Act: -0.0001

Data Index: 546298 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4449. Min Act: -0.0001

Data Index: 639235 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1262138 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1064882 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.6882. Min Range: -0.6882

Max Act: 0.4439. Min Act: -0.0001

Data Index: 449813 (C4 (Web Text))

Max Activating Token Index: 297