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

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

Neuron 4049 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: 0.5895. Min Range: -0.5895

Max Act: 0.5895. Min Act: -0.0000

Data Index: 804517 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5544. Min Act: -0.0000

Data Index: 590541 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1359221 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5084. Min Act: -0.0000

Data Index: 683634 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5295. Min Act: -0.0000

Data Index: 872231 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5235. Min Act: -0.0000

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5244. Min Act: -0.0000

Data Index: 302170 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5387. Min Act: -0.0000

Data Index: 680256 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5118. Min Act: -0.0000

Data Index: 925542 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5082. Min Act: -0.0000

Data Index: 53864 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5048. Min Act: -0.0000

Data Index: 244559 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5213. Min Act: -0.0000

Data Index: 69539 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5028. Min Act: -0.0000

Data Index: 643391 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.5111. Min Act: -0.0000

Data Index: 497041 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1217964 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.4747. Min Act: -0.0000

Data Index: 483850 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1233035 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.4763. Min Act: -0.0000

Data Index: 32208 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.4652. Min Act: -0.0000

Data Index: 828735 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.5895. Min Range: -0.5895

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1309311 (C4 (Web Text))

Max Activating Token Index: 686