Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2009 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0003

Data Index: 355828 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0520. Min Act: -0.0003

Data Index: 133913 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0528. Min Act: -0.0003

Data Index: 654867 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0513. Min Act: -0.0003

Data Index: 392073 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0506. Min Act: -0.0003

Data Index: 790342 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0509. Min Act: -0.0002

Data Index: 768737 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0527. Min Act: -0.0003

Data Index: 48553 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0491. Min Act: -0.0003

Data Index: 187439 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0491. Min Act: -0.0003

Data Index: 301949 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1279535 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0466. Min Act: -0.0004

Data Index: 41177 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0468. Min Act: -0.0003

Data Index: 68455 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0462. Min Act: -0.0003

Data Index: 508532 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0454. Min Act: -0.0003

Data Index: 666069 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0463. Min Act: -0.0003

Data Index: 83360 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1151698 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0442. Min Act: -0.0003

Data Index: 966083 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0453. Min Act: -0.0003

Data Index: 38624 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0444. Min Act: -0.0003

Data Index: 828327 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0444. Min Act: -0.0003

Data Index: 848528 (C4 (Web Text))

Max Activating Token Index: 106