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

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

Neuron 4321 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.8436. Min Act: -0.0000

Data Index: 55766 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.4153. Min Act: -0.0001

Data Index: 240903 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.3949. Min Act: -0.0001

Data Index: 76589 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.5444. Min Act: -0.0000

Data Index: 179905 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.2690. Min Act: -0.0000

Data Index: 702662 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.2486. Min Act: -0.0001

Data Index: 319868 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.3487. Min Act: -0.0000

Data Index: 360298 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.0882. Min Act: -0.0000

Data Index: 437822 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.0760. Min Act: -0.0001

Data Index: 148388 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.0300. Min Act: -0.0001

Data Index: 705710 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.1298. Min Act: -0.0001

Data Index: 804900 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 1.8436. Min Range: -1.8436

Max Act: 0.9700. Min Act: -0.0000

Data Index: 386119 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.0237. Min Act: -0.0000

Data Index: 1285299 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1252551 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.8436. Min Range: -1.8436

Max Act: 0.9844. Min Act: -0.0000

Data Index: 121608 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.8436. Min Range: -1.8436

Max Act: 0.9619. Min Act: -0.0000

Data Index: 6208 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 1.8436. Min Range: -1.8436

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1213429 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.8436. Min Range: -1.8436

Max Act: 0.9383. Min Act: -0.0000

Data Index: 534208 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.8436. Min Range: -1.8436

Max Act: 0.8610. Min Act: -0.0001

Data Index: 431715 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.8436. Min Range: -1.8436

Max Act: 1.0378. Min Act: -0.0000

Data Index: 624043 (C4 (Web Text))

Max Activating Token Index: 330