Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1039 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.6010. Min Act: -0.0000

Data Index: 381655 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.6941. Min Act: -0.0000

Data Index: 1218616 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.4720. Min Act: -0.0000

Data Index: 171583 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.3678. Min Act: -0.0001

Data Index: 511995 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.4775. Min Act: -0.0001

Data Index: 279774 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.3229. Min Act: -0.0001

Data Index: 971376 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.4379. Min Act: -0.0000

Data Index: 826373 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.4182. Min Act: -0.0001

Data Index: 80588 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.3263. Min Act: -0.0000

Data Index: 704291 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.3395. Min Act: -0.0000

Data Index: 121248 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1270434 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.2834. Min Act: -0.0000

Data Index: 291379 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1303657 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.1978. Min Act: -0.0001

Data Index: 267906 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.0937. Min Act: -0.0001

Data Index: 445058 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1095756 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.3057. Min Act: -0.0000

Data Index: 448984 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.1777. Min Act: -0.0000

Data Index: 866077 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.0791. Min Act: -0.0000

Data Index: 323999 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.6941. Min Range: -1.6941

Max Act: 1.2180. Min Act: -0.0000

Data Index: 660742 (C4 (Web Text))

Max Activating Token Index: 527