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

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

Neuron 4729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.8033. Min Act: -0.0000

Data Index: 3272 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.8014. Min Act: -0.0000

Data Index: 664379 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6961. Min Act: -0.0000

Data Index: 176008 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6122. Min Act: -0.0000

Data Index: 130699 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5979. Min Act: -0.0000

Data Index: 507444 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1327680 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5169. Min Act: -0.0000

Data Index: 871797 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1069829 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5082. Min Act: -0.0000

Data Index: 473493 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4875. Min Act: -0.0000

Data Index: 47078 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4996. Min Act: -0.0000

Data Index: 106862 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4766. Min Act: -0.0000

Data Index: 319385 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.5039. Min Act: -0.0000

Data Index: 57445 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4624. Min Act: -0.0000

Data Index: 74517 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4326. Min Act: -0.0000

Data Index: 537253 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1115917 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1329392 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1005858 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4461. Min Act: -0.0000

Data Index: 611907 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.8033. Min Range: -0.8033

Max Act: 0.4924. Min Act: -0.0000

Data Index: 897399 (C4 (Web Text))

Max Activating Token Index: 903