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

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

Neuron 276 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.8071. Min Act: -0.0001

Data Index: 442599 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.7349. Min Act: -0.0001

Data Index: 82448 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6248. Min Act: -0.0001

Data Index: 522734 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6134. Min Act: -0.0001

Data Index: 1215521 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5968. Min Act: -0.0001

Data Index: 293628 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6342. Min Act: -0.0001

Data Index: 404206 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5752. Min Act: -0.0001

Data Index: 678047 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.6321. Min Act: -0.0001

Data Index: 1205782 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5655. Min Act: -0.0001

Data Index: 930832 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5773. Min Act: -0.0001

Data Index: 791314 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5796. Min Act: -0.0001

Data Index: 796916 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5495. Min Act: -0.0001

Data Index: 96260 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5640. Min Act: -0.0001

Data Index: 364102 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1180879 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5727. Min Act: -0.0001

Data Index: 674344 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5356. Min Act: -0.0001

Data Index: 365873 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5706. Min Act: -0.0001

Data Index: 58288 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5534. Min Act: -0.0001

Data Index: 633692 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5798. Min Act: -0.0001

Data Index: 658296 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.8071. Min Range: -0.8071

Max Act: 0.5448. Min Act: -0.0001

Data Index: 380227 (C4 (Web Text))

Max Activating Token Index: 917