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

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

Neuron 2387 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1587304 (Python Code)

Max Activating Token Index: 522

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1278005 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0628. Min Act: -0.0002

Data Index: 149815 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1097729 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1571488 (Python Code)

Max Activating Token Index: 274

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1231379 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0585. Min Act: -0.0002

Data Index: 503812 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1419883 (Python Code)

Max Activating Token Index: 474

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0557. Min Act: -0.0002

Data Index: 45534 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0576. Min Act: -0.0002

Data Index: 221226 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1630766 (Python Code)

Max Activating Token Index: 232

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0572. Min Act: -0.0002

Data Index: 993315 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1050793 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0556. Min Act: -0.0002

Data Index: 781440 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0569. Min Act: -0.0002

Data Index: 378013 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0573. Min Act: -0.0002

Data Index: 888416 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1310256 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0585. Min Act: -0.0002

Data Index: 865145 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0542. Min Act: -0.0002

Data Index: 771782 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1120262 (C4 (Web Text))

Max Activating Token Index: 959