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

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

Neuron 2573 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: 0.5110. Min Range: -0.5110

Max Act: 0.4867. Min Act: -0.0001

Data Index: 1230038 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.5110. Min Act: -0.0001

Data Index: 1401857 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4828. Min Act: -0.0000

Data Index: 579077 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4831. Min Act: -0.0001

Data Index: 409987 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4680. Min Act: -0.0001

Data Index: 1268460 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4655. Min Act: -0.0001

Data Index: 1370362 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4467. Min Act: -0.0000

Data Index: 425103 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1566443 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1363263 (Python Code)

Max Activating Token Index: 729

Text #9

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4477. Min Act: -0.0001

Data Index: 1583359 (Python Code)

Max Activating Token Index: 393

Text #10

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4314. Min Act: -0.0001

Data Index: 1634984 (Python Code)

Max Activating Token Index: 745

Text #11

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4423. Min Act: -0.0000

Data Index: 649311 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4307. Min Act: -0.0001

Data Index: 260042 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4280. Min Act: -0.0000

Data Index: 459108 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1062359 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4005. Min Act: -0.0001

Data Index: 978767 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1552027 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4373. Min Act: -0.0000

Data Index: 604006 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4655. Min Act: -0.0001

Data Index: 1464374 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 0.5110. Min Range: -0.5110

Max Act: 0.4323. Min Act: -0.0000

Data Index: 545791 (C4 (Web Text))

Max Activating Token Index: 862