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

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

Neuron 2003 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: 0.6904. Min Range: -0.6904

Max Act: 0.6904. Min Act: -0.0000

Data Index: 303523 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5772. Min Act: -0.0000

Data Index: 431527 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5342. Min Act: -0.0000

Data Index: 945318 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4853. Min Act: -0.0000

Data Index: 104678 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1079129 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4829. Min Act: -0.0000

Data Index: 357130 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1200694 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4326. Min Act: -0.0000

Data Index: 225839 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1079820 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4300. Min Act: -0.0000

Data Index: 910671 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4538. Min Act: -0.0000

Data Index: 215837 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.3689. Min Act: -0.0000

Data Index: 655354 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1274845 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1083050 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.3818. Min Act: -0.0000

Data Index: 49373 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.3936. Min Act: -0.0000

Data Index: 946338 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4245. Min Act: -0.0000

Data Index: 492280 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.3823. Min Act: -0.0000

Data Index: 379418 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.3494. Min Act: -0.0000

Data Index: 1289403 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.6904. Min Range: -0.6904

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1510556 (Python Code)

Max Activating Token Index: 66