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

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

Neuron 5815 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.4362. Min Act: -0.0002

Data Index: 1322039 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3844. Min Act: -0.0002

Data Index: 374842 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.4031. Min Act: -0.0002

Data Index: 206552 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3989. Min Act: -0.0002

Data Index: 920867 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3522. Min Act: -0.0002

Data Index: 675866 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3691. Min Act: -0.0002

Data Index: 993032 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2947. Min Act: -0.0002

Data Index: 767385 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3033. Min Act: -0.0002

Data Index: 116864 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2960. Min Act: -0.0002

Data Index: 766624 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.3125. Min Act: -0.0002

Data Index: 1268945 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2609. Min Act: -0.0002

Data Index: 187112 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2561. Min Act: -0.0002

Data Index: 405607 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2623. Min Act: -0.0002

Data Index: 938198 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2603. Min Act: -0.0002

Data Index: 873603 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2627. Min Act: -0.0002

Data Index: 1197350 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2345. Min Act: -0.0002

Data Index: 1202273 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2858. Min Act: -0.0002

Data Index: 601906 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2638. Min Act: -0.0002

Data Index: 249009 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2362. Min Act: -0.0002

Data Index: 167238 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 1.4362. Min Range: -1.4362

Max Act: 1.2514. Min Act: -0.0002

Data Index: 1253454 (C4 (Web Text))

Max Activating Token Index: 25