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

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

Neuron 5563 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1207100 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1437976 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1534512 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1318038 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1021712 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5491. Min Act: -0.0001

Data Index: 1051444 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5611. Min Act: -0.0001

Data Index: 986315 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5295. Min Act: -0.0000

Data Index: 405972 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5435. Min Act: -0.0000

Data Index: 746951 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5386. Min Act: -0.0000

Data Index: 535021 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5042. Min Act: -0.0001

Data Index: 387344 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5538. Min Act: -0.0000

Data Index: 595687 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4497. Min Act: -0.0000

Data Index: 666053 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4968. Min Act: -0.0000

Data Index: 747897 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4334. Min Act: -0.0000

Data Index: 578078 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4865. Min Act: -0.0000

Data Index: 322749 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5163. Min Act: -0.0001

Data Index: 1141172 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.5126. Min Act: -0.0000

Data Index: 533110 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4957. Min Act: -0.0000

Data Index: 499634 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.7012. Min Range: -0.7012

Max Act: 0.4299. Min Act: -0.0001

Data Index: 37512 (C4 (Web Text))

Max Activating Token Index: 931