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

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

Neuron 3200 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: 1.2402. Min Range: -1.2402

Max Act: 1.2402. Min Act: -0.0002

Data Index: 1151485 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1937. Min Act: -0.0002

Data Index: 1021983 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1550. Min Act: -0.0002

Data Index: 269 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1624. Min Act: -0.0002

Data Index: 1164401 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1338. Min Act: -0.0002

Data Index: 1279291 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1196. Min Act: -0.0002

Data Index: 210626 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1089. Min Act: -0.0003

Data Index: 822707 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0975. Min Act: -0.0002

Data Index: 892861 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1162. Min Act: -0.0002

Data Index: 462779 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.1187. Min Act: -0.0002

Data Index: 884318 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0916. Min Act: -0.0002

Data Index: 1117854 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0837. Min Act: -0.0002

Data Index: 287676 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0800. Min Act: -0.0002

Data Index: 959556 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0748. Min Act: -0.0002

Data Index: 582771 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0831. Min Act: -0.0002

Data Index: 1212746 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0823. Min Act: -0.0002

Data Index: 1337215 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0785. Min Act: -0.0002

Data Index: 735545 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0731. Min Act: -0.0002

Data Index: 623325 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0654. Min Act: -0.0002

Data Index: 366196 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.2402. Min Range: -1.2402

Max Act: 1.0661. Min Act: -0.0002

Data Index: 538187 (C4 (Web Text))

Max Activating Token Index: 83