Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4568 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.5723. Min Act: -0.0000

Data Index: 1382041 (Python Code)

Max Activating Token Index: 307

Text #1

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1099186 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1599535 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.1281. Min Act: -0.0000

Data Index: 1113865 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1578086 (Python Code)

Max Activating Token Index: 830

Text #5

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0838. Min Act: -0.0000

Data Index: 405456 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0528. Min Act: 0.0000

Data Index: 1166267 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1450495 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 1.5723. Min Range: -1.5723

Max Act: 1.0075. Min Act: -0.0000

Data Index: 887346 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8956. Min Act: -0.0000

Data Index: 106202 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8978. Min Act: -0.0000

Data Index: 34500 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1487583 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1485082 (Python Code)

Max Activating Token Index: 1006

Text #13

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1317039 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1168468 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1084393 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1193210 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1055081 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.9026. Min Act: -0.0000

Data Index: 358056 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.5723. Min Range: -1.5723

Max Act: 0.8953. Min Act: 0.0000

Data Index: 1583333 (Python Code)

Max Activating Token Index: 137