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

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

Neuron 4655 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: 1.5663. Min Range: -1.5663

Max Act: 1.5663. Min Act: -0.0000

Data Index: 126681 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1284564 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1037335 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9734. Min Act: -0.0000

Data Index: 379622 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.7916. Min Act: -0.0000

Data Index: 344308 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.0127. Min Act: -0.0000

Data Index: 158100 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8896. Min Act: -0.0000

Data Index: 182864 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.9320. Min Act: -0.0000

Data Index: 644419 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1314765 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1344301 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.7883. Min Act: -0.0000

Data Index: 218512 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.7941. Min Act: -0.0000

Data Index: 596364 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.7811. Min Act: -0.0000

Data Index: 94425 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8147. Min Act: -0.0000

Data Index: 747499 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8682. Min Act: -0.0000

Data Index: 289457 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8081. Min Act: -0.0000

Data Index: 271005 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.7614. Min Act: -0.0000

Data Index: 26821 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1323495 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.7472. Min Act: -0.0000

Data Index: 840123 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.5663. Min Range: -1.5663

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1139582 (C4 (Web Text))

Max Activating Token Index: 638