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

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

Neuron 2385 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0440. Min Range: -2.0440

Max Act: 2.0440. Min Act: -0.0000

Data Index: 271216 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.7507. Min Act: -0.0000

Data Index: 998644 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.5007. Min Act: -0.0000

Data Index: 1284927 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.2339. Min Act: -0.0001

Data Index: 1480440 (Python Code)

Max Activating Token Index: 173

Text #4

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.2017. Min Act: -0.0000

Data Index: 999289 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0968. Min Act: -0.0001

Data Index: 1397470 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.2073. Min Act: -0.0000

Data Index: 417150 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0715. Min Act: -0.0000

Data Index: 292713 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.1653. Min Act: -0.0000

Data Index: 214465 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0119. Min Act: -0.0000

Data Index: 760719 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0381. Min Act: -0.0000

Data Index: 349350 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0518. Min Act: -0.0000

Data Index: 1011829 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.1291. Min Act: -0.0000

Data Index: 543179 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0705. Min Act: 0.0000

Data Index: 1430703 (Python Code)

Max Activating Token Index: 649

Text #14

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.1408. Min Act: -0.0000

Data Index: 476744 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0914. Min Act: -0.0000

Data Index: 597762 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0852. Min Act: -0.0000

Data Index: 465239 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1402678 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 2.0440. Min Range: -2.0440

Max Act: 1.0835. Min Act: -0.0000

Data Index: 952324 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.0440. Min Range: -2.0440

Max Act: 0.9602. Min Act: -0.0000

Data Index: 304409 (C4 (Web Text))

Max Activating Token Index: 478