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

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

Neuron 4925 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: 2.0621. Min Range: -2.0621

Max Act: 2.0621. Min Act: -0.0000

Data Index: 1027349 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1210827 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.6624. Min Act: -0.0000

Data Index: 586756 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.6051. Min Act: -0.0000

Data Index: 527821 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1106097 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.6918. Min Act: -0.0000

Data Index: 450801 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.5191. Min Act: -0.0000

Data Index: 640054 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.5007. Min Act: -0.0000

Data Index: 268810 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1380657 (Python Code)

Max Activating Token Index: 922

Text #9

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.4907. Min Act: 0.0000

Data Index: 220510 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.4637. Min Act: -0.0000

Data Index: 396250 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.5397. Min Act: -0.0000

Data Index: 897453 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.4260. Min Act: -0.0000

Data Index: 305580 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.4289. Min Act: -0.0000

Data Index: 559025 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.4313. Min Act: -0.0000

Data Index: 820538 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.4015. Min Act: -0.0000

Data Index: 1509447 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.3960. Min Act: -0.0000

Data Index: 788196 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1138169 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.3742. Min Act: -0.0000

Data Index: 123471 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 2.0621. Min Range: -2.0621

Max Act: 1.3635. Min Act: -0.0000

Data Index: 245922 (C4 (Web Text))

Max Activating Token Index: 695