Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4961 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7757. Min Act: -0.0000

Data Index: 636589 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6129. Min Act: -0.0000

Data Index: 473981 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1450365 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6123. Min Act: -0.0000

Data Index: 597637 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6325. Min Act: -0.0000

Data Index: 563417 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1032640 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1199203 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5756. Min Act: -0.0000

Data Index: 402154 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1518564 (Python Code)

Max Activating Token Index: 369

Text #9

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5514. Min Act: -0.0000

Data Index: 388848 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5632. Min Act: -0.0000

Data Index: 807439 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1271521 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5302. Min Act: -0.0000

Data Index: 17643 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5332. Min Act: -0.0000

Data Index: 147254 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5775. Min Act: -0.0000

Data Index: 716421 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1045969 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5340. Min Act: -0.0000

Data Index: 244042 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1602077 (Python Code)

Max Activating Token Index: 684

Text #18

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1313234 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.4769. Min Act: -0.0000

Data Index: 412131 (C4 (Web Text))

Max Activating Token Index: 639