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

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

Neuron 3608 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.2059. Min Act: -0.0000

Data Index: 38951 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1079170 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1308711 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1691. Min Act: -0.0000

Data Index: 239381 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1286214 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1182256 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1250773 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1713. Min Act: -0.0000

Data Index: 698464 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1664. Min Act: -0.0000

Data Index: 812165 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1159069 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1639. Min Act: -0.0000

Data Index: 759623 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1582. Min Act: -0.0000

Data Index: 25001 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1044169 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1498. Min Act: -0.0001

Data Index: 65790 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1576. Min Act: -0.0001

Data Index: 532140 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1479. Min Act: -0.0000

Data Index: 379291 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1237315 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1382. Min Act: -0.0001

Data Index: 935042 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1379. Min Act: -0.0001

Data Index: 721046 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1404. Min Act: -0.0000

Data Index: 214552 (C4 (Web Text))

Max Activating Token Index: 716