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

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

Neuron 210 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: 0.4437. Min Range: -0.4437

Max Act: 0.3984. Min Act: -0.0001

Data Index: 940720 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4131. Min Act: -0.0001

Data Index: 984305 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4173. Min Act: -0.0001

Data Index: 862443 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4437. Min Act: -0.0001

Data Index: 849311 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1126362 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3367. Min Act: -0.0000

Data Index: 636888 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3552. Min Act: -0.0001

Data Index: 362245 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4132. Min Act: -0.0001

Data Index: 486805 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3953. Min Act: -0.0000

Data Index: 944879 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3505. Min Act: -0.0001

Data Index: 187510 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3749. Min Act: -0.0000

Data Index: 389790 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3675. Min Act: -0.0001

Data Index: 536266 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3478. Min Act: -0.0000

Data Index: 941163 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3120. Min Act: -0.0000

Data Index: 848947 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3126. Min Act: -0.0000

Data Index: 665798 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3173. Min Act: -0.0000

Data Index: 765651 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2921. Min Act: -0.0000

Data Index: 37626 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2900. Min Act: -0.0001

Data Index: 1437778 (Python Code)

Max Activating Token Index: 412

Text #18

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3054. Min Act: -0.0001

Data Index: 995648 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1195829 (C4 (Web Text))

Max Activating Token Index: 553