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

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

Neuron 432 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.7071. Min Act: -0.0000

Data Index: 107251 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.5949. Min Act: -0.0000

Data Index: 1199926 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1142238 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.5108. Min Act: -0.0000

Data Index: 892645 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.5079. Min Act: -0.0000

Data Index: 104534 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.4474. Min Act: -0.0000

Data Index: 342179 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.4865. Min Act: -0.0000

Data Index: 588581 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.4616. Min Act: -0.0000

Data Index: 316846 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2980. Min Act: -0.0000

Data Index: 271859 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.3656. Min Act: -0.0000

Data Index: 231832 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.3337. Min Act: -0.0000

Data Index: 513477 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2413. Min Act: -0.0000

Data Index: 800347 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1248616 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2283. Min Act: -0.0000

Data Index: 640741 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2470. Min Act: -0.0000

Data Index: 684817 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2974. Min Act: -0.0000

Data Index: 375502 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2183. Min Act: -0.0000

Data Index: 198587 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2914. Min Act: -0.0000

Data Index: 855464 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.1604. Min Act: -0.0000

Data Index: 565408 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.7071. Min Range: -1.7071

Max Act: 1.2046. Min Act: -0.0000

Data Index: 691297 (C4 (Web Text))

Max Activating Token Index: 488