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

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

Neuron 2922 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: 0.4708. Min Range: -0.4708

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1020391 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1003484 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3525. Min Act: -0.0000

Data Index: 22163 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1106089 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3259. Min Act: -0.0000

Data Index: 70781 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3064. Min Act: -0.0000

Data Index: 471335 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2987. Min Act: -0.0000

Data Index: 138424 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2971. Min Act: -0.0000

Data Index: 54442 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1125288 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1056046 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3002. Min Act: -0.0000

Data Index: 916379 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3126. Min Act: -0.0000

Data Index: 58760 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.3193. Min Act: -0.0000

Data Index: 756329 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2846. Min Act: -0.0000

Data Index: 70851 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1023565 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2829. Min Act: -0.0000

Data Index: 682166 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2627. Min Act: -0.0000

Data Index: 572050 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2726. Min Act: -0.0000

Data Index: 258447 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2630. Min Act: -0.0000

Data Index: 325846 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.4708. Min Range: -0.4708

Max Act: 0.2755. Min Act: -0.0000

Data Index: 63515 (C4 (Web Text))

Max Activating Token Index: 350