Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4445. Min Act: -0.0001

Data Index: 1521686 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4309. Min Act: -0.0001

Data Index: 1433815 (Python Code)

Max Activating Token Index: 155

Text #2

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3583. Min Act: -0.0001

Data Index: 1466531 (Python Code)

Max Activating Token Index: 626

Text #3

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.4132. Min Act: -0.0001

Data Index: 1418210 (Python Code)

Max Activating Token Index: 999

Text #4

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3728. Min Act: -0.0001

Data Index: 1452153 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3666. Min Act: -0.0001

Data Index: 1434828 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3674. Min Act: -0.0001

Data Index: 1556755 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3762. Min Act: -0.0001

Data Index: 1553878 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3865. Min Act: -0.0001

Data Index: 1529317 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3732. Min Act: -0.0001

Data Index: 1384795 (Python Code)

Max Activating Token Index: 50

Text #10

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3619. Min Act: -0.0001

Data Index: 1473448 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3952. Min Act: -0.0001

Data Index: 1492800 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1466477 (Python Code)

Max Activating Token Index: 164

Text #13

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1628575 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3674. Min Act: -0.0001

Data Index: 1555712 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1422167 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3412. Min Act: -0.0001

Data Index: 1608211 (Python Code)

Max Activating Token Index: 623

Text #17

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3681. Min Act: -0.0001

Data Index: 1373772 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3424. Min Act: -0.0001

Data Index: 1510376 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 0.4445. Min Range: -0.4445

Max Act: 0.3862. Min Act: -0.0001

Data Index: 1639926 (Python Code)

Max Activating Token Index: 777