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

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

Neuron 780 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: 0.0872. Min Range: -0.0872

Max Act: 0.0872. Min Act: -0.0002

Data Index: 468067 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0591. Min Act: -0.0002

Data Index: 272320 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1169476 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0488. Min Act: -0.0002

Data Index: 582673 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0493. Min Act: -0.0002

Data Index: 758523 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0484. Min Act: -0.0002

Data Index: 620143 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0466. Min Act: -0.0002

Data Index: 310980 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0451. Min Act: -0.0002

Data Index: 894831 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0438. Min Act: -0.0002

Data Index: 737930 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0462. Min Act: -0.0002

Data Index: 693396 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0443. Min Act: -0.0002

Data Index: 307374 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0430. Min Act: -0.0002

Data Index: 63990 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0428. Min Act: -0.0002

Data Index: 450676 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0432. Min Act: -0.0002

Data Index: 884775 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0430. Min Act: -0.0002

Data Index: 664334 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0418. Min Act: -0.0002

Data Index: 281864 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0425. Min Act: -0.0002

Data Index: 904675 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0398. Min Act: -0.0002

Data Index: 222764 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0396. Min Act: -0.0002

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0380. Min Act: -0.0002

Data Index: 352754 (C4 (Web Text))

Max Activating Token Index: 994