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

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

Neuron 2549 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.5514. Min Act: -0.0001

Data Index: 254234 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.6120. Min Act: -0.0001

Data Index: 303240 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.5164. Min Act: -0.0001

Data Index: 195440 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1129731 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4998. Min Act: -0.0001

Data Index: 444533 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4974. Min Act: -0.0001

Data Index: 84664 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4761. Min Act: -0.0001

Data Index: 549863 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4977. Min Act: -0.0001

Data Index: 240267 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4548. Min Act: -0.0001

Data Index: 766367 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4179. Min Act: -0.0001

Data Index: 1179928 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3961. Min Act: -0.0001

Data Index: 388784 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4223. Min Act: -0.0001

Data Index: 297982 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3893. Min Act: -0.0001

Data Index: 1226953 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4957. Min Act: -0.0001

Data Index: 397125 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3989. Min Act: -0.0001

Data Index: 100036 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4618. Min Act: -0.0001

Data Index: 44498 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4280. Min Act: -0.0001

Data Index: 716886 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4044. Min Act: -0.0001

Data Index: 307472 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.4168. Min Act: -0.0001

Data Index: 953647 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.6120. Min Range: -0.6120

Max Act: 0.3508. Min Act: -0.0001

Data Index: 6508 (C4 (Web Text))

Max Activating Token Index: 298