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

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

Neuron 3681 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: 0.7020. Min Range: -0.7020

Max Act: 0.7020. Min Act: -0.0001

Data Index: 1234751 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6541. Min Act: -0.0001

Data Index: 1121252 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6480. Min Act: -0.0000

Data Index: 146911 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.6629. Min Act: -0.0001

Data Index: 1406692 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1391774 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5731. Min Act: -0.0001

Data Index: 905663 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1586562 (Python Code)

Max Activating Token Index: 965

Text #7

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1532191 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5593. Min Act: -0.0001

Data Index: 675302 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1108500 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5549. Min Act: -0.0001

Data Index: 728993 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5550. Min Act: -0.0001

Data Index: 264086 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5312. Min Act: -0.0001

Data Index: 688783 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5293. Min Act: -0.0000

Data Index: 835553 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5376. Min Act: -0.0000

Data Index: 895433 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.4992. Min Act: -0.0001

Data Index: 1202097 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5266. Min Act: -0.0001

Data Index: 425175 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5393. Min Act: -0.0000

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.5366. Min Act: -0.0000

Data Index: 696284 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.7020. Min Range: -0.7020

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1052100 (C4 (Web Text))

Max Activating Token Index: 737