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

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

Neuron 2525 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.6493. Min Act: -0.0001

Data Index: 247557 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4986. Min Act: -0.0001

Data Index: 366360 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4938. Min Act: -0.0001

Data Index: 1100080 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1189472 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4820. Min Act: -0.0001

Data Index: 676562 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4602. Min Act: -0.0001

Data Index: 594515 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3773. Min Act: -0.0001

Data Index: 590368 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4547. Min Act: -0.0001

Data Index: 1240638 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4563. Min Act: -0.0001

Data Index: 642730 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4635. Min Act: -0.0001

Data Index: 1347039 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4307. Min Act: -0.0001

Data Index: 660814 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4506. Min Act: -0.0001

Data Index: 696162 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3845. Min Act: -0.0001

Data Index: 1315092 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4222. Min Act: -0.0001

Data Index: 1108403 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4392. Min Act: -0.0001

Data Index: 290657 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4374. Min Act: -0.0001

Data Index: 1037182 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4065. Min Act: -0.0001

Data Index: 838476 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5000. Min Act: -0.0001

Data Index: 54430 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4325. Min Act: -0.0001

Data Index: 803179 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4511. Min Act: -0.0001

Data Index: 385902 (C4 (Web Text))

Max Activating Token Index: 907