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

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

Neuron 1413 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: 2.0544. Min Range: -2.0544

Max Act: 2.0544. Min Act: -0.0000

Data Index: 745146 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.8250. Min Act: -0.0000

Data Index: 1105868 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.8996. Min Act: -0.0000

Data Index: 1144897 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.8532. Min Act: -0.0000

Data Index: 288947 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.7699. Min Act: -0.0000

Data Index: 768361 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.8489. Min Act: -0.0000

Data Index: 589013 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.7254. Min Act: -0.0000

Data Index: 375131 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.6672. Min Act: -0.0000

Data Index: 896528 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.6562. Min Act: -0.0000

Data Index: 253064 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.5610. Min Act: -0.0000

Data Index: 701143 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.7268. Min Act: -0.0000

Data Index: 235617 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.7160. Min Act: -0.0000

Data Index: 860446 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.5984. Min Act: -0.0000

Data Index: 704259 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.6710. Min Act: -0.0000

Data Index: 210893 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.6500. Min Act: -0.0000

Data Index: 970062 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4511. Min Act: -0.0000

Data Index: 117388 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4239. Min Act: -0.0000

Data Index: 769996 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4006. Min Act: -0.0000

Data Index: 141907 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4911. Min Act: -0.0000

Data Index: 869443 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 2.0544. Min Range: -2.0544

Max Act: 1.4133. Min Act: -0.0000

Data Index: 358094 (C4 (Web Text))

Max Activating Token Index: 960