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

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

Neuron 3633 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4481. Min Range: -1.4481

Max Act: 1.4481. Min Act: -0.0000

Data Index: 523733 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.4481. Min Range: -1.4481

Max Act: 1.1234. Min Act: -0.0000

Data Index: 570732 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 1.4481. Min Range: -1.4481

Max Act: 1.1477. Min Act: -0.0000

Data Index: 636855 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.8723. Min Act: -0.0000

Data Index: 713770 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.9282. Min Act: -0.0000

Data Index: 621623 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.8830. Min Act: -0.0000

Data Index: 381378 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7990. Min Act: -0.0000

Data Index: 737221 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7900. Min Act: -0.0000

Data Index: 711156 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.8199. Min Act: -0.0000

Data Index: 277629 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.8001. Min Act: -0.0000

Data Index: 334727 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1331113 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7863. Min Act: -0.0000

Data Index: 93450 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.8215. Min Act: -0.0000

Data Index: 835107 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7741. Min Act: -0.0000

Data Index: 46982 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7678. Min Act: -0.0000

Data Index: 896307 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7567. Min Act: -0.0000

Data Index: 66424 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7576. Min Act: -0.0000

Data Index: 28536 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1114750 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.7416. Min Act: -0.0000

Data Index: 744406 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.4481. Min Range: -1.4481

Max Act: 0.8404. Min Act: -0.0000

Data Index: 126281 (C4 (Web Text))

Max Activating Token Index: 309