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

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

Neuron 3102 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.9899. Min Act: -0.0000

Data Index: 1265791 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8943. Min Act: -0.0000

Data Index: 694365 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8319. Min Act: -0.0000

Data Index: 149252 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8944. Min Act: -0.0000

Data Index: 292942 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8575. Min Act: -0.0000

Data Index: 716932 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8224. Min Act: -0.0000

Data Index: 69107 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8236. Min Act: -0.0000

Data Index: 3701 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8086. Min Act: -0.0000

Data Index: 354863 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.8047. Min Act: -0.0000

Data Index: 419871 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7853. Min Act: -0.0000

Data Index: 86421 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7652. Min Act: -0.0000

Data Index: 550515 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7415. Min Act: -0.0000

Data Index: 415953 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7467. Min Act: -0.0000

Data Index: 740704 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7611. Min Act: -0.0000

Data Index: 407934 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1160615 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1117486 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7503. Min Act: -0.0000

Data Index: 496246 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7508. Min Act: -0.0000

Data Index: 840517 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7325. Min Act: -0.0000

Data Index: 834717 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.9899. Min Range: -0.9899

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1049995 (C4 (Web Text))

Max Activating Token Index: 942