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

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

Neuron 115 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.6046. Min Act: -0.0000

Data Index: 459789 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5510. Min Act: -0.0000

Data Index: 514567 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5554. Min Act: -0.0001

Data Index: 1301219 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5356. Min Act: -0.0000

Data Index: 588210 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1065473 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1210043 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4693. Min Act: -0.0000

Data Index: 946949 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5142. Min Act: -0.0000

Data Index: 851178 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5129. Min Act: -0.0000

Data Index: 81878 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4769. Min Act: -0.0000

Data Index: 603142 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.5064. Min Act: -0.0000

Data Index: 779202 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4518. Min Act: -0.0001

Data Index: 605276 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4909. Min Act: -0.0000

Data Index: 589069 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4490. Min Act: -0.0000

Data Index: 334303 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4580. Min Act: -0.0001

Data Index: 88659 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1343293 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4697. Min Act: -0.0000

Data Index: 381896 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4672. Min Act: -0.0000

Data Index: 574357 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1108032 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.6046. Min Range: -0.6046

Max Act: 0.4544. Min Act: -0.0000

Data Index: 297164 (C4 (Web Text))

Max Activating Token Index: 130