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

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

Neuron 873 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.6474. Min Act: -0.0000

Data Index: 920090 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.5571. Min Act: -0.0000

Data Index: 637726 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.5219. Min Act: -0.0000

Data Index: 72746 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.4678. Min Act: -0.0000

Data Index: 537511 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.4474. Min Act: -0.0000

Data Index: 252773 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.4106. Min Act: -0.0000

Data Index: 27562 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.3814. Min Act: -0.0000

Data Index: 24976 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1087405 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.3529. Min Act: -0.0000

Data Index: 109146 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1584715 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1393502 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1384290 (Python Code)

Max Activating Token Index: 672

Text #12

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1028084 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1488762 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2361. Min Act: -0.0000

Data Index: 884419 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2541. Min Act: -0.0000

Data Index: 594363 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1517172 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2462. Min Act: -0.0000

Data Index: 1402734 (Python Code)

Max Activating Token Index: 350

Text #18

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1600803 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 0.6474. Min Range: -0.6474

Max Act: 0.2305. Min Act: -0.0000

Data Index: 611546 (C4 (Web Text))

Max Activating Token Index: 613