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

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

Neuron 6077 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1015650 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5977. Min Act: -0.0000

Data Index: 145457 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1252708 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4905. Min Act: -0.0000

Data Index: 612311 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4856. Min Act: -0.0000

Data Index: 792017 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4750. Min Act: -0.0000

Data Index: 802511 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1025225 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3787. Min Act: -0.0000

Data Index: 93076 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3759. Min Act: -0.0000

Data Index: 109105 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1128110 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4008. Min Act: -0.0000

Data Index: 889678 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1229737 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3675. Min Act: -0.0000

Data Index: 993503 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3719. Min Act: -0.0000

Data Index: 287270 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1129463 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3443. Min Act: -0.0000

Data Index: 318543 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3586. Min Act: -0.0000

Data Index: 275215 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3781. Min Act: -0.0000

Data Index: 153399 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3529. Min Act: -0.0000

Data Index: 911418 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.3640. Min Act: -0.0000

Data Index: 603444 (C4 (Web Text))

Max Activating Token Index: 576