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

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

Neuron 599 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7621. Min Range: -2.7621

Max Act: 2.7621. Min Act: -0.0000

Data Index: 777115 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 2.7621. Min Range: -2.7621

Max Act: 2.4736. Min Act: -0.0000

Data Index: 586015 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 2.7621. Min Range: -2.7621

Max Act: 2.0908. Min Act: -0.0000

Data Index: 30263 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 2.7621. Min Range: -2.7621

Max Act: 2.1956. Min Act: -0.0000

Data Index: 937173 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 2.7621. Min Range: -2.7621

Max Act: 2.1377. Min Act: -0.0000

Data Index: 1069351 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 2.7621. Min Range: -2.7621

Max Act: 2.0741. Min Act: -0.0000

Data Index: 908100 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.9587. Min Act: -0.0000

Data Index: 775815 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.8401. Min Act: -0.0000

Data Index: 1163000 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.8519. Min Act: -0.0001

Data Index: 884625 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.6568. Min Act: -0.0000

Data Index: 1325690 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.7363. Min Act: -0.0000

Data Index: 494534 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.8408. Min Act: -0.0001

Data Index: 1032726 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.7825. Min Act: -0.0000

Data Index: 509804 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.7891. Min Act: -0.0000

Data Index: 439699 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.6600. Min Act: -0.0000

Data Index: 146044 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.5968. Min Act: -0.0000

Data Index: 418633 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1348572 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.7394. Min Act: -0.0000

Data Index: 56800 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.6022. Min Act: -0.0000

Data Index: 287123 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 2.7621. Min Range: -2.7621

Max Act: 1.6263. Min Act: -0.0001

Data Index: 272108 (C4 (Web Text))

Max Activating Token Index: 384