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

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

Neuron 278 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1979. Min Act: -0.0001

Data Index: 244691 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1544882 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1400724 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1839. Min Act: -0.0001

Data Index: 1007448 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1763. Min Act: -0.0001

Data Index: 1141580 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1771. Min Act: -0.0001

Data Index: 691641 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1600089 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1672. Min Act: -0.0001

Data Index: 327556 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1705. Min Act: -0.0001

Data Index: 973393 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1096896 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1421192 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1689. Min Act: -0.0001

Data Index: 290212 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1637. Min Act: -0.0001

Data Index: 28638 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1654. Min Act: -0.0001

Data Index: 414757 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1665. Min Act: -0.0001

Data Index: 833646 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1303139 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1596. Min Act: -0.0001

Data Index: 533850 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1587. Min Act: -0.0001

Data Index: 996523 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1458611 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 0.1979. Min Range: -0.1979

Max Act: 0.1404. Min Act: -0.0001

Data Index: 428426 (C4 (Web Text))

Max Activating Token Index: 585