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

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

Neuron 574 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2758. Min Range: -3.2758

Max Act: 3.2758. Min Act: -0.0000

Data Index: 335035 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 3.2758. Min Range: -3.2758

Max Act: 3.2450. Min Act: -0.0000

Data Index: 1180319 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.6471. Min Act: -0.0000

Data Index: 760109 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.7071. Min Act: -0.0000

Data Index: 627942 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.6106. Min Act: -0.0000

Data Index: 452821 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.3398. Min Act: -0.0000

Data Index: 1327850 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.6392. Min Act: -0.0000

Data Index: 1101639 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1318950 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.3142. Min Act: -0.0000

Data Index: 758571 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.4823. Min Act: -0.0000

Data Index: 195423 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.5441. Min Act: -0.0000

Data Index: 599476 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.3033. Min Act: -0.0000

Data Index: 942374 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.0796. Min Act: -0.0000

Data Index: 299081 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.2629. Min Act: -0.0000

Data Index: 1357008 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.3682. Min Act: -0.0000

Data Index: 478067 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.2417. Min Act: -0.0000

Data Index: 765537 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.0093. Min Act: -0.0000

Data Index: 221228 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.0719. Min Act: -0.0000

Data Index: 752970 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.2969. Min Act: -0.0000

Data Index: 915298 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 3.2758. Min Range: -3.2758

Max Act: 2.1687. Min Act: -0.0000

Data Index: 1003443 (C4 (Web Text))

Max Activating Token Index: 435