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

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

Neuron 1487 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.9365. Min Act: -0.0000

Data Index: 5805 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.4707. Min Act: -0.0000

Data Index: 277447 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.5666. Min Act: -0.0000

Data Index: 332219 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.5835. Min Act: -0.0000

Data Index: 1642948 (Python Code)

Max Activating Token Index: 930

Text #4

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.4897. Min Act: -0.0000

Data Index: 817229 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.2209. Min Act: -0.0000

Data Index: 957275 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.0950. Min Act: -0.0000

Data Index: 761344 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.9284. Min Act: -0.0000

Data Index: 767392 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.9962. Min Act: -0.0000

Data Index: 396527 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.0052. Min Act: -0.0000

Data Index: 999197 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.1029. Min Act: -0.0000

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.6487. Min Act: -0.0000

Data Index: 1191445 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 2.9365. Min Range: -2.9365

Max Act: 2.0420. Min Act: -0.0000

Data Index: 300713 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.8191. Min Act: -0.0000

Data Index: 712114 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.8017. Min Act: -0.0000

Data Index: 216403 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.7951. Min Act: -0.0000

Data Index: 1583029 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.6691. Min Act: -0.0000

Data Index: 371365 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.7603. Min Act: -0.0000

Data Index: 1162453 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1143162 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 2.9365. Min Range: -2.9365

Max Act: 1.7490. Min Act: -0.0000

Data Index: 546788 (C4 (Web Text))

Max Activating Token Index: 646