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

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

Neuron 5018 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.8025. Min Act: -0.0002

Data Index: 598406 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.8303. Min Act: -0.0002

Data Index: 323387 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7889. Min Act: -0.0002

Data Index: 635085 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7057. Min Act: -0.0002

Data Index: 329920 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7058. Min Act: -0.0002

Data Index: 1004574 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7428. Min Act: -0.0002

Data Index: 809941 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7545. Min Act: -0.0002

Data Index: 1248793 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6387. Min Act: -0.0002

Data Index: 928494 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6760. Min Act: -0.0002

Data Index: 765733 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6305. Min Act: -0.0002

Data Index: 11420 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6855. Min Act: -0.0002

Data Index: 455667 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6983. Min Act: -0.0002

Data Index: 1000275 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5928. Min Act: -0.0002

Data Index: 146714 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6310. Min Act: -0.0002

Data Index: 1354744 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6594. Min Act: -0.0002

Data Index: 517276 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7257. Min Act: -0.0002

Data Index: 66713 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6732. Min Act: -0.0002

Data Index: 686472 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5970. Min Act: -0.0002

Data Index: 1253795 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6803. Min Act: -0.0002

Data Index: 470494 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6731. Min Act: -0.0002

Data Index: 1140019 (C4 (Web Text))

Max Activating Token Index: 328