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

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

Neuron 3224 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0302. Min Range: -1.0302

Max Act: 1.0302. Min Act: -0.0000

Data Index: 528187 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1636169 (Python Code)

Max Activating Token Index: 854

Text #2

Max Range: 1.0302. Min Range: -1.0302

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1254185 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1187926 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8774. Min Act: -0.0000

Data Index: 923467 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.9183. Min Act: -0.0000

Data Index: 939401 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8953. Min Act: -0.0000

Data Index: 1195137 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.9658. Min Act: -0.0000

Data Index: 483306 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8979. Min Act: -0.0000

Data Index: 373311 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.9137. Min Act: -0.0000

Data Index: 980425 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1474800 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8383. Min Act: -0.0000

Data Index: 310423 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8547. Min Act: -0.0000

Data Index: 559663 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.9066. Min Act: -0.0000

Data Index: 936853 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1550589 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8235. Min Act: -0.0000

Data Index: 478364 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1410617 (Python Code)

Max Activating Token Index: 935

Text #17

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.7782. Min Act: -0.0000

Data Index: 667122 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1186131 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.0302. Min Range: -1.0302

Max Act: 0.8061. Min Act: -0.0000

Data Index: 917222 (C4 (Web Text))

Max Activating Token Index: 297