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

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

Neuron 3692 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6731. Min Range: -2.6731

Max Act: 2.6731. Min Act: -0.0000

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 2.6731. Min Range: -2.6731

Max Act: 2.4254. Min Act: -0.0000

Data Index: 1300305 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 2.6731. Min Range: -2.6731

Max Act: 2.2990. Min Act: -0.0000

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.7142. Min Act: -0.0000

Data Index: 1101943 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.7103. Min Act: -0.0000

Data Index: 474547 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.5227. Min Act: -0.0000

Data Index: 258436 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.5039. Min Act: -0.0000

Data Index: 675714 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.5749. Min Act: -0.0000

Data Index: 376060 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.5449. Min Act: -0.0000

Data Index: 560970 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.5642. Min Act: -0.0000

Data Index: 1348991 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.5516. Min Act: -0.0000

Data Index: 971868 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.6084. Min Act: -0.0000

Data Index: 337620 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.6039. Min Act: -0.0000

Data Index: 512286 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.5139. Min Act: -0.0000

Data Index: 1020136 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.4216. Min Act: -0.0000

Data Index: 851850 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.2967. Min Act: -0.0000

Data Index: 1189613 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.2676. Min Act: -0.0000

Data Index: 1247361 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.2388. Min Act: -0.0000

Data Index: 639894 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.1977. Min Act: -0.0000

Data Index: 261308 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 2.6731. Min Range: -2.6731

Max Act: 1.1360. Min Act: -0.0000

Data Index: 21201 (C4 (Web Text))

Max Activating Token Index: 550