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

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

Neuron 3137 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8637. Min Act: -0.0000

Data Index: 231366 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7981. Min Act: -0.0000

Data Index: 38158 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1153141 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8123. Min Act: -0.0000

Data Index: 1310298 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8068. Min Act: -0.0000

Data Index: 259340 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1099729 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.8333. Min Act: -0.0000

Data Index: 487948 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7498. Min Act: -0.0000

Data Index: 656514 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7685. Min Act: -0.0000

Data Index: 553349 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7571. Min Act: -0.0000

Data Index: 950014 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7263. Min Act: -0.0000

Data Index: 435097 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7438. Min Act: -0.0000

Data Index: 430680 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7192. Min Act: -0.0000

Data Index: 7970 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.7050. Min Act: -0.0000

Data Index: 127746 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6592. Min Act: -0.0000

Data Index: 773222 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6986. Min Act: -0.0000

Data Index: 697766 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1067650 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6893. Min Act: -0.0000

Data Index: 696562 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6862. Min Act: -0.0000

Data Index: 335162 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.8637. Min Range: -0.8637

Max Act: 0.6637. Min Act: -0.0000

Data Index: 955936 (C4 (Web Text))

Max Activating Token Index: 597