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

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

Neuron 5358 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: 2.3739. Min Range: -2.3739

Max Act: 2.3739. Min Act: -0.0000

Data Index: 597153 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 2.3739. Min Range: -2.3739

Max Act: 2.2218. Min Act: -0.0000

Data Index: 305895 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 2.3739. Min Range: -2.3739

Max Act: 2.0439. Min Act: -0.0000

Data Index: 654148 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.9618. Min Act: -0.0000

Data Index: 431029 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.9466. Min Act: -0.0000

Data Index: 623077 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 2.3739. Min Range: -2.3739

Max Act: 2.1111. Min Act: -0.0000

Data Index: 1309917 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.8679. Min Act: -0.0000

Data Index: 689953 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.9301. Min Act: -0.0000

Data Index: 1185890 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.9347. Min Act: -0.0000

Data Index: 465051 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 2.3739. Min Range: -2.3739

Max Act: 2.0314. Min Act: -0.0000

Data Index: 926714 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.8906. Min Act: -0.0000

Data Index: 811555 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.8657. Min Act: -0.0000

Data Index: 609677 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.7743. Min Act: -0.0000

Data Index: 1058308 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.9035. Min Act: -0.0000

Data Index: 275387 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.9075. Min Act: -0.0000

Data Index: 334199 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.6900. Min Act: -0.0000

Data Index: 446200 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.8708. Min Act: -0.0000

Data Index: 482817 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.7726. Min Act: -0.0000

Data Index: 472459 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.7441. Min Act: -0.0000

Data Index: 676439 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 2.3739. Min Range: -2.3739

Max Act: 1.7393. Min Act: -0.0000

Data Index: 299889 (C4 (Web Text))

Max Activating Token Index: 8