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

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

Neuron 2018 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: 1.4688. Min Range: -1.4688

Max Act: 1.4688. Min Act: -0.0000

Data Index: 575106 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.2922. Min Act: -0.0000

Data Index: 1320206 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.2066. Min Act: -0.0000

Data Index: 50292 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.2127. Min Act: -0.0000

Data Index: 754187 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1247281 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9662. Min Act: -0.0000

Data Index: 593728 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.0569. Min Act: -0.0000

Data Index: 1319187 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.4688. Min Range: -1.4688

Max Act: 1.0075. Min Act: -0.0000

Data Index: 700279 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9745. Min Act: -0.0000

Data Index: 256829 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9356. Min Act: -0.0000

Data Index: 380076 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1050948 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9803. Min Act: -0.0000

Data Index: 835005 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9487. Min Act: -0.0000

Data Index: 194485 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9343. Min Act: -0.0000

Data Index: 113919 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8442. Min Act: -0.0000

Data Index: 638407 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8917. Min Act: -0.0000

Data Index: 324553 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.9152. Min Act: -0.0000

Data Index: 615881 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1183424 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1074041 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.4688. Min Range: -1.4688

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1284834 (C4 (Web Text))

Max Activating Token Index: 19