Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 868 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0001

Data Index: 206881 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0514. Min Act: -0.0001

Data Index: 664936 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0472. Min Act: -0.0001

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0478. Min Act: -0.0001

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0435. Min Act: -0.0001

Data Index: 877773 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0408. Min Act: -0.0001

Data Index: 625716 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0387. Min Act: -0.0001

Data Index: 526972 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0409. Min Act: -0.0001

Data Index: 291296 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0364. Min Act: -0.0001

Data Index: 668210 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0366. Min Act: -0.0001

Data Index: 844278 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0410. Min Act: -0.0001

Data Index: 358171 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1381038 (Python Code)

Max Activating Token Index: 78

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1595897 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0357. Min Act: -0.0001

Data Index: 287212 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0351. Min Act: -0.0001

Data Index: 900986 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1066199 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0318. Min Act: -0.0001

Data Index: 407028 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0343. Min Act: -0.0001

Data Index: 1364614 (Python Code)

Max Activating Token Index: 1002

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0330. Min Act: -0.0001

Data Index: 203212 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0333. Min Act: -0.0001

Data Index: 681300 (C4 (Web Text))

Max Activating Token Index: 287