Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3545 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.7839. Min Range: -5.7839

Max Act: 5.7839. Min Act: -0.0000

Data Index: 1342539 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.3047. Min Act: -0.0000

Data Index: 1149033 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.7411. Min Act: -0.0000

Data Index: 1041234 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.6085. Min Act: -0.0000

Data Index: 249148 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.7195. Min Act: -0.0000

Data Index: 1022191 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.5062. Min Act: -0.0000

Data Index: 268531 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.3945. Min Act: -0.0000

Data Index: 599830 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.2414. Min Act: -0.0000

Data Index: 1347628 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.0543. Min Act: -0.0000

Data Index: 457497 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.9464. Min Act: -0.0000

Data Index: 282042 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.9274. Min Act: -0.0000

Data Index: 645011 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.7476. Min Act: -0.0000

Data Index: 701659 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.7070. Min Act: -0.0000

Data Index: 370516 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 5.7839. Min Range: -5.7839

Max Act: 4.1987. Min Act: -0.0000

Data Index: 1259933 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.6820. Min Act: -0.0000

Data Index: 1130782 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.7945. Min Act: -0.0000

Data Index: 420338 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.5706. Min Act: -0.0000

Data Index: 201303 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.7114. Min Act: -0.0000

Data Index: 366508 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.4849. Min Act: -0.0000

Data Index: 296023 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 5.7839. Min Range: -5.7839

Max Act: 3.6298. Min Act: -0.0000

Data Index: 1045465 (C4 (Web Text))

Max Activating Token Index: 334