Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3494 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.7503. Min Act: -0.0001

Data Index: 641718 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1345857 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6990. Min Act: -0.0001

Data Index: 793608 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6900. Min Act: -0.0001

Data Index: 305047 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.7024. Min Act: -0.0001

Data Index: 539595 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6774. Min Act: -0.0001

Data Index: 381000 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6562. Min Act: -0.0001

Data Index: 700091 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6816. Min Act: -0.0001

Data Index: 9935 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6594. Min Act: -0.0001

Data Index: 396638 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6755. Min Act: -0.0001

Data Index: 1432507 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.7007. Min Act: -0.0001

Data Index: 675314 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1498389 (Python Code)

Max Activating Token Index: 853

Text #12

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6644. Min Act: -0.0001

Data Index: 1250999 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6583. Min Act: -0.0001

Data Index: 1279272 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6805. Min Act: -0.0001

Data Index: 1262536 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6612. Min Act: -0.0001

Data Index: 1567318 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1324722 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6592. Min Act: -0.0001

Data Index: 1247141 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6493. Min Act: -0.0001

Data Index: 135488 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6317. Min Act: -0.0001

Data Index: 1147257 (C4 (Web Text))

Max Activating Token Index: 90