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

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

Neuron 4907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.4539. Min Act: -0.0000

Data Index: 446181 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 5.0288. Min Range: -5.0288

Max Act: 5.0288. Min Act: -0.0000

Data Index: 228633 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3687. Min Act: -0.0000

Data Index: 127404 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3687. Min Act: -0.0000

Data Index: 633206 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3687. Min Act: -0.0000

Data Index: 231904 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3687. Min Act: -0.0000

Data Index: 190235 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3687. Min Act: -0.0000

Data Index: 513833 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3687. Min Act: -0.0000

Data Index: 1341843 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 5.0288. Min Range: -5.0288

Max Act: 3.6115. Min Act: -0.0000

Data Index: 1185243 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.2527. Min Act: -0.0000

Data Index: 157680 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3895. Min Act: -0.0000

Data Index: 603497 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3233. Min Act: -0.0000

Data Index: 1212399 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.2937. Min Act: -0.0000

Data Index: 1341357 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.0276. Min Act: -0.0000

Data Index: 960990 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.1655. Min Act: -0.0000

Data Index: 1284285 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.0781. Min Act: -0.0000

Data Index: 941796 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.2488. Min Act: -0.0000

Data Index: 379843 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 5.0288. Min Range: -5.0288

Max Act: 3.8608. Min Act: -0.0000

Data Index: 598783 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 5.0288. Min Range: -5.0288

Max Act: 4.3687. Min Act: -0.0000

Data Index: 133528 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 5.0288. Min Range: -5.0288

Max Act: 3.9753. Min Act: -0.0000

Data Index: 903820 (C4 (Web Text))

Max Activating Token Index: 656