Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1427 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.3697. Min Act: -0.0000

Data Index: 1217546 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.3602. Min Act: -0.0000

Data Index: 350310 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0598. Min Act: -0.0000

Data Index: 780411 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.1852. Min Act: -0.0000

Data Index: 29914 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 1.3697. Min Range: -1.3697

Max Act: 1.0519. Min Act: -0.0000

Data Index: 128540 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9224. Min Act: -0.0000

Data Index: 926599 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.9121. Min Act: -0.0000

Data Index: 817269 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1196425 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8754. Min Act: -0.0000

Data Index: 321086 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8681. Min Act: -0.0000

Data Index: 193708 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8739. Min Act: -0.0000

Data Index: 545378 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8142. Min Act: -0.0000

Data Index: 507775 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7808. Min Act: -0.0000

Data Index: 820039 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1029639 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7739. Min Act: -0.0000

Data Index: 205330 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7505. Min Act: -0.0000

Data Index: 966281 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8054. Min Act: -0.0000

Data Index: 633987 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7499. Min Act: -0.0000

Data Index: 905527 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.7632. Min Act: -0.0000

Data Index: 113051 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.3697. Min Range: -1.3697

Max Act: 0.8232. Min Act: -0.0000

Data Index: 662697 (C4 (Web Text))

Max Activating Token Index: 805