Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2600 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.6171. Min Act: -0.0000

Data Index: 753045 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 2.1545. Min Range: -2.1545

Max Act: 2.1545. Min Act: -0.0000

Data Index: 454564 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.8113. Min Act: -0.0000

Data Index: 982635 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.4381. Min Act: -0.0000

Data Index: 212923 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.6391. Min Act: -0.0000

Data Index: 220112 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.5252. Min Act: -0.0000

Data Index: 474075 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.6473. Min Act: -0.0000

Data Index: 858871 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.5118. Min Act: -0.0000

Data Index: 1563182 (Python Code)

Max Activating Token Index: 339

Text #8

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.5066. Min Act: -0.0000

Data Index: 31642 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.5651. Min Act: -0.0000

Data Index: 269256 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.5478. Min Act: -0.0000

Data Index: 627572 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.4756. Min Act: -0.0000

Data Index: 205780 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.3900. Min Act: -0.0000

Data Index: 923142 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.3980. Min Act: -0.0000

Data Index: 183244 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.3430. Min Act: -0.0000

Data Index: 266298 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.4952. Min Act: -0.0000

Data Index: 50339 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.4983. Min Act: -0.0000

Data Index: 624611 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.4864. Min Act: -0.0000

Data Index: 1182861 (C4 (Web Text))

Max Activating Token Index: 849

Text #18

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.4078. Min Act: -0.0000

Data Index: 934700 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 2.1545. Min Range: -2.1545

Max Act: 1.6306. Min Act: -0.0000

Data Index: 754230 (C4 (Web Text))

Max Activating Token Index: 727