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

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

Neuron 1097 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.4927. Min Act: -0.0000

Data Index: 376135 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.4070. Min Act: -0.0000

Data Index: 508261 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.2295. Min Act: -0.0000

Data Index: 833745 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.7883. Min Act: -0.0000

Data Index: 534237 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.0834. Min Act: -0.0000

Data Index: 214617 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 3.4927. Min Range: -3.4927

Max Act: 3.0341. Min Act: -0.0000

Data Index: 330015 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.7419. Min Act: -0.0000

Data Index: 1604358 (Python Code)

Max Activating Token Index: 301

Text #7

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.8536. Min Act: -0.0000

Data Index: 1343462 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.9544. Min Act: -0.0000

Data Index: 1277727 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.7893. Min Act: -0.0000

Data Index: 673627 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.9191. Min Act: -0.0000

Data Index: 717390 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.6376. Min Act: -0.0000

Data Index: 30264 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.7415. Min Act: -0.0000

Data Index: 169590 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.7385. Min Act: -0.0000

Data Index: 1341187 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.8766. Min Act: -0.0000

Data Index: 703510 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.5861. Min Act: -0.0000

Data Index: 616820 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.6958. Min Act: -0.0000

Data Index: 219945 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.6786. Min Act: -0.0000

Data Index: 295153 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.6699. Min Act: -0.0000

Data Index: 1433372 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 3.4927. Min Range: -3.4927

Max Act: 2.6616. Min Act: -0.0000

Data Index: 130803 (C4 (Web Text))

Max Activating Token Index: 144