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

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

Neuron 4214 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: 0.7484. Min Range: -0.7484

Max Act: 0.7484. Min Act: -0.0002

Data Index: 306510 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7301. Min Act: -0.0002

Data Index: 1344336 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7416. Min Act: -0.0002

Data Index: 1397765 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7121. Min Act: -0.0002

Data Index: 1394872 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7069. Min Act: -0.0002

Data Index: 1373746 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7118. Min Act: -0.0002

Data Index: 225467 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.7015. Min Act: -0.0002

Data Index: 1179272 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6912. Min Act: -0.0002

Data Index: 1395331 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6804. Min Act: -0.0002

Data Index: 737438 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6804. Min Act: -0.0002

Data Index: 916182 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6615. Min Act: -0.0002

Data Index: 1252680 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6725. Min Act: -0.0002

Data Index: 1532511 (Python Code)

Max Activating Token Index: 683

Text #12

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6529. Min Act: -0.0002

Data Index: 1166530 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6549. Min Act: -0.0002

Data Index: 617029 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6498. Min Act: -0.0002

Data Index: 1380277 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6447. Min Act: -0.0002

Data Index: 880157 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6577. Min Act: -0.0002

Data Index: 1479402 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6427. Min Act: -0.0002

Data Index: 1510868 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6377. Min Act: -0.0002

Data Index: 309929 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.7484. Min Range: -0.7484

Max Act: 0.6360. Min Act: -0.0002

Data Index: 1007592 (C4 (Web Text))

Max Activating Token Index: 814