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

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

Neuron 5563 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.8162. Min Act: 0.0000

Data Index: 972677 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1224973 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.5437. Min Act: -0.0000

Data Index: 52968 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.4014. Min Act: 0.0000

Data Index: 293519 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3702. Min Act: -0.0000

Data Index: 232378 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3290. Min Act: -0.0000

Data Index: 1216340 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3503. Min Act: -0.0000

Data Index: 967161 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3311. Min Act: -0.0000

Data Index: 266258 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3327. Min Act: -0.0000

Data Index: 461409 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3339. Min Act: 0.0000

Data Index: 528435 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3069. Min Act: -0.0000

Data Index: 74263 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3146. Min Act: -0.0000

Data Index: 969287 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3116. Min Act: -0.0000

Data Index: 900436 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3023. Min Act: -0.0000

Data Index: 869151 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.3200. Min Act: -0.0000

Data Index: 500002 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.2625. Min Act: 0.0000

Data Index: 1275680 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.2912. Min Act: 0.0000

Data Index: 1357876 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.2858. Min Act: -0.0000

Data Index: 96180 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.2841. Min Act: -0.0000

Data Index: 646403 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.8162. Min Range: -0.8162

Max Act: 0.2761. Min Act: -0.0000

Data Index: 625645 (C4 (Web Text))

Max Activating Token Index: 324