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

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

Neuron 4891 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: 0.7103. Min Range: -0.7103

Max Act: 0.7103. Min Act: -0.0000

Data Index: 547684 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.5323. Min Act: -0.0000

Data Index: 731776 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4894. Min Act: -0.0000

Data Index: 441332 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4882. Min Act: -0.0000

Data Index: 436346 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1277598 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.5081. Min Act: -0.0000

Data Index: 653113 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4960. Min Act: -0.0000

Data Index: 771615 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1267132 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1210965 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4665. Min Act: -0.0000

Data Index: 354593 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4685. Min Act: -0.0000

Data Index: 548062 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4678. Min Act: -0.0000

Data Index: 871305 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1341074 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3781. Min Act: -0.0000

Data Index: 917631 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4694. Min Act: -0.0000

Data Index: 634111 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1055496 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1112672 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4313. Min Act: -0.0000

Data Index: 773782 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4147. Min Act: -0.0000

Data Index: 86291 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3828. Min Act: -0.0000

Data Index: 52415 (C4 (Web Text))

Max Activating Token Index: 668