Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1930 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.6321. Min Act: -0.0000

Data Index: 434672 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.6278. Min Act: -0.0000

Data Index: 869021 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5805. Min Act: -0.0000

Data Index: 566881 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1321730 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1351904 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5395. Min Act: -0.0000

Data Index: 609885 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5212. Min Act: -0.0000

Data Index: 63902 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5166. Min Act: -0.0000

Data Index: 588079 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1301141 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5442. Min Act: -0.0000

Data Index: 942067 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5218. Min Act: -0.0000

Data Index: 941908 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5127. Min Act: -0.0000

Data Index: 148789 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4948. Min Act: -0.0000

Data Index: 830032 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4982. Min Act: -0.0000

Data Index: 405634 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4907. Min Act: -0.0000

Data Index: 6077 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5260. Min Act: -0.0000

Data Index: 895069 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1144521 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.5047. Min Act: -0.0000

Data Index: 814736 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4803. Min Act: -0.0000

Data Index: 670189 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.6321. Min Range: -0.6321

Max Act: 0.4928. Min Act: -0.0000

Data Index: 451088 (C4 (Web Text))

Max Activating Token Index: 397