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

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

Neuron 2837 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: 0.5930. Min Range: -0.5930

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1341469 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1352696 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1357611 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5251. Min Act: -0.0000

Data Index: 378625 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5030. Min Act: -0.0000

Data Index: 780060 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4707. Min Act: -0.0000

Data Index: 111036 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4530. Min Act: -0.0000

Data Index: 353129 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4828. Min Act: -0.0000

Data Index: 518397 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1254390 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4288. Min Act: -0.0000

Data Index: 70262 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4702. Min Act: -0.0000

Data Index: 521413 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1082518 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4383. Min Act: -0.0000

Data Index: 763421 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3546. Min Act: -0.0000

Data Index: 176975 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3566. Min Act: -0.0000

Data Index: 154121 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4193. Min Act: -0.0000

Data Index: 283780 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3847. Min Act: -0.0000

Data Index: 63839 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4405. Min Act: -0.0000

Data Index: 396513 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4129. Min Act: -0.0000

Data Index: 250018 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1269776 (C4 (Web Text))

Max Activating Token Index: 791