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

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

Neuron 3514 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.8000. Min Act: -0.0001

Data Index: 647722 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.5379. Min Act: -0.0001

Data Index: 328559 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.3647. Min Act: -0.0001

Data Index: 452365 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.6143. Min Act: -0.0000

Data Index: 639015 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.4326. Min Act: -0.0001

Data Index: 50999 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.4314. Min Act: -0.0000

Data Index: 344975 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.3512. Min Act: -0.0001

Data Index: 631337 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.3445. Min Act: -0.0001

Data Index: 489911 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.4135. Min Act: -0.0001

Data Index: 705234 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.2150. Min Act: -0.0001

Data Index: 531493 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.2021. Min Act: -0.0001

Data Index: 99553 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.0730. Min Act: -0.0001

Data Index: 338866 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.0873. Min Act: -0.0000

Data Index: 506211 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.1926. Min Act: -0.0001

Data Index: 124417 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.0709. Min Act: -0.0001

Data Index: 1230545 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.0450. Min Act: -0.0001

Data Index: 1069030 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.0117. Min Act: -0.0000

Data Index: 1198508 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 2.8000. Min Range: -2.8000

Max Act: 2.0054. Min Act: -0.0001

Data Index: 98427 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.8683. Min Act: -0.0001

Data Index: 342284 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 2.8000. Min Range: -2.8000

Max Act: 1.9810. Min Act: -0.0000

Data Index: 994271 (C4 (Web Text))

Max Activating Token Index: 355