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

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

Neuron 2155 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: 3.0722. Min Range: -3.0722

Max Act: 3.0722. Min Act: -0.0000

Data Index: 1277232 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.8692. Min Act: -0.0000

Data Index: 1131960 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.9917. Min Act: -0.0000

Data Index: 1135333 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.9396. Min Act: -0.0000

Data Index: 359657 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.7974. Min Act: -0.0000

Data Index: 1308696 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.7871. Min Act: -0.0000

Data Index: 380692 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.8414. Min Act: -0.0000

Data Index: 1326998 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.8314. Min Act: -0.0000

Data Index: 1339116 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.7888. Min Act: -0.0000

Data Index: 787563 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.8072. Min Act: -0.0000

Data Index: 701117 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.3775. Min Act: -0.0000

Data Index: 15692 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.7869. Min Act: -0.0000

Data Index: 626392 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.6015. Min Act: -0.0000

Data Index: 271700 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.5646. Min Act: -0.0000

Data Index: 804393 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.6855. Min Act: -0.0000

Data Index: 383527 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.6604. Min Act: -0.0000

Data Index: 522163 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.5270. Min Act: -0.0000

Data Index: 141437 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.5187. Min Act: -0.0000

Data Index: 28651 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.5022. Min Act: -0.0000

Data Index: 457677 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 3.0722. Min Range: -3.0722

Max Act: 2.4898. Min Act: -0.0000

Data Index: 1309176 (C4 (Web Text))

Max Activating Token Index: 665