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

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

Neuron 4900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4148. Min Act: -0.0000

Data Index: 891728 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.5564. Min Act: -0.0000

Data Index: 1220544 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.2524. Min Act: -0.0000

Data Index: 198504 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3401. Min Act: -0.0000

Data Index: 1411052 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.2407. Min Act: -0.0000

Data Index: 497428 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.1944. Min Act: -0.0000

Data Index: 685479 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.1951. Min Act: -0.0000

Data Index: 735903 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.0718. Min Act: -0.0000

Data Index: 1131176 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3119. Min Act: -0.0000

Data Index: 840103 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.2932. Min Act: -0.0000

Data Index: 1008832 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.1551. Min Act: -0.0000

Data Index: 836332 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 3.5564. Min Range: -3.5564

Max Act: 2.9467. Min Act: -0.0000

Data Index: 967545 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.0858. Min Act: -0.0000

Data Index: 187800 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 3.5564. Min Range: -3.5564

Max Act: 2.5230. Min Act: -0.0000

Data Index: 1433771 (Python Code)

Max Activating Token Index: 977

Text #14

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.0226. Min Act: -0.0000

Data Index: 1591820 (Python Code)

Max Activating Token Index: 140

Text #15

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.0154. Min Act: -0.0000

Data Index: 1641070 (Python Code)

Max Activating Token Index: 971

Text #16

Max Range: 3.5564. Min Range: -3.5564

Max Act: 2.8000. Min Act: -0.0000

Data Index: 1492660 (Python Code)

Max Activating Token Index: 812

Text #17

Max Range: 3.5564. Min Range: -3.5564

Max Act: 2.9924. Min Act: -0.0000

Data Index: 1609374 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 3.5564. Min Range: -3.5564

Max Act: 2.9910. Min Act: -0.0000

Data Index: 808417 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 3.5564. Min Range: -3.5564

Max Act: 2.9744. Min Act: -0.0000

Data Index: 858688 (C4 (Web Text))

Max Activating Token Index: 746