Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2643 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1276026 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5752. Min Act: -0.0001

Data Index: 1317519 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5486. Min Act: -0.0001

Data Index: 572045 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4952. Min Act: -0.0001

Data Index: 636445 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5039. Min Act: -0.0001

Data Index: 874739 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4471. Min Act: -0.0001

Data Index: 404865 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5398. Min Act: -0.0001

Data Index: 1153721 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4868. Min Act: -0.0001

Data Index: 742807 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.3958. Min Act: -0.0001

Data Index: 838008 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4136. Min Act: -0.0001

Data Index: 448736 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.3919. Min Act: -0.0001

Data Index: 70878 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4476. Min Act: -0.0001

Data Index: 975463 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4051. Min Act: -0.0001

Data Index: 1180862 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.3996. Min Act: -0.0001

Data Index: 196003 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.3833. Min Act: -0.0001

Data Index: 521928 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.3922. Min Act: -0.0001

Data Index: 94074 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4096. Min Act: -0.0001

Data Index: 1019637 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4110. Min Act: -0.0001

Data Index: 622265 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.3816. Min Act: -0.0001

Data Index: 334613 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4038. Min Act: -0.0001

Data Index: 814370 (C4 (Web Text))

Max Activating Token Index: 935