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

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

Neuron 3255 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.6956. Min Act: -0.0001

Data Index: 740089 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4170. Min Act: -0.0001

Data Index: 577948 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4990. Min Act: -0.0001

Data Index: 306928 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4812. Min Act: -0.0001

Data Index: 739401 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.4343. Min Act: -0.0001

Data Index: 1266415 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.3127. Min Act: -0.0001

Data Index: 687500 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.3438. Min Act: -0.0001

Data Index: 1289001 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1220314 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.3791. Min Act: -0.0001

Data Index: 218652 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2872. Min Act: -0.0001

Data Index: 26435 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.3331. Min Act: -0.0001

Data Index: 883493 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2442. Min Act: -0.0001

Data Index: 813743 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2263. Min Act: -0.0001

Data Index: 786321 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.2609. Min Act: -0.0001

Data Index: 486726 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.1279. Min Act: -0.0001

Data Index: 89309 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.1299. Min Act: -0.0001

Data Index: 569002 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.1588. Min Act: -0.0001

Data Index: 1232278 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.1093. Min Act: -0.0001

Data Index: 239947 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.0938. Min Act: -0.0001

Data Index: 937962 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 1.6956. Min Range: -1.6956

Max Act: 1.1134. Min Act: -0.0001

Data Index: 611256 (C4 (Web Text))

Max Activating Token Index: 582