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

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

Neuron 5446 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.5492. Min Act: -0.0000

Data Index: 319966 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4543. Min Act: -0.0000

Data Index: 810424 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4411. Min Act: -0.0000

Data Index: 546928 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4506. Min Act: -0.0000

Data Index: 57641 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4604. Min Act: -0.0000

Data Index: 489649 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4382. Min Act: -0.0000

Data Index: 5106 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1027925 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4156. Min Act: -0.0000

Data Index: 898480 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1164539 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4272. Min Act: -0.0000

Data Index: 998109 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1157413 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4017. Min Act: -0.0000

Data Index: 648373 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3949. Min Act: -0.0000

Data Index: 765188 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3774. Min Act: -0.0000

Data Index: 346062 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3899. Min Act: -0.0000

Data Index: 516556 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1325628 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3845. Min Act: -0.0000

Data Index: 408799 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4110. Min Act: -0.0000

Data Index: 868580 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4166. Min Act: -0.0000

Data Index: 557862 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1534949 (Python Code)

Max Activating Token Index: 249