Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2589 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.8296. Min Act: -0.0001

Data Index: 149509 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7959. Min Act: -0.0001

Data Index: 1166490 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7558. Min Act: -0.0001

Data Index: 518411 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.7186. Min Act: -0.0001

Data Index: 433936 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.5905. Min Act: -0.0001

Data Index: 697777 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6478. Min Act: -0.0001

Data Index: 1220159 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6524. Min Act: -0.0001

Data Index: 1127013 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6322. Min Act: -0.0001

Data Index: 206997 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6713. Min Act: -0.0001

Data Index: 720945 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6571. Min Act: -0.0001

Data Index: 793329 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6685. Min Act: -0.0001

Data Index: 558670 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6540. Min Act: -0.0001

Data Index: 1002039 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1420561 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6047. Min Act: -0.0001

Data Index: 1580511 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6544. Min Act: -0.0001

Data Index: 1462568 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6099. Min Act: -0.0001

Data Index: 863005 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6319. Min Act: -0.0001

Data Index: 523071 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6470. Min Act: -0.0001

Data Index: 341499 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6057. Min Act: -0.0001

Data Index: 527001 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.8296. Min Range: -0.8296

Max Act: 0.6231. Min Act: -0.0001

Data Index: 223822 (C4 (Web Text))

Max Activating Token Index: 137