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

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

Neuron 3023 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1274147 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3670. Min Act: -0.0000

Data Index: 903602 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1033186 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3201. Min Act: -0.0000

Data Index: 211306 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2997. Min Act: -0.0000

Data Index: 62042 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2887. Min Act: -0.0000

Data Index: 645653 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.3135. Min Act: -0.0000

Data Index: 898151 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1525035 (Python Code)

Max Activating Token Index: 925

Text #8

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1488032 (Python Code)

Max Activating Token Index: 730

Text #9

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1029853 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2642. Min Act: -0.0000

Data Index: 815129 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2632. Min Act: -0.0000

Data Index: 463172 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2605. Min Act: -0.0000

Data Index: 654022 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2610. Min Act: -0.0000

Data Index: 77003 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1586410 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2230. Min Act: -0.0000

Data Index: 223628 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1488729 (Python Code)

Max Activating Token Index: 258

Text #17

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1113094 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2309. Min Act: -0.0000

Data Index: 220295 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.3670. Min Range: -0.3670

Max Act: 0.2454. Min Act: -0.0000

Data Index: 614261 (C4 (Web Text))

Max Activating Token Index: 379