Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2563 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3825. Min Act: -0.0000

Data Index: 267905 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3850. Min Act: 0.0001

Data Index: 1186176 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3699. Min Act: -0.0001

Data Index: 109069 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3467. Min Act: -0.0000

Data Index: 448716 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3541. Min Act: -0.0000

Data Index: 795463 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3595. Min Act: -0.0000

Data Index: 997042 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3271. Min Act: -0.0000

Data Index: 137230 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3385. Min Act: -0.0000

Data Index: 364379 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3303. Min Act: -0.0001

Data Index: 648029 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3126. Min Act: -0.0000

Data Index: 172486 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.3034. Min Act: -0.0001

Data Index: 280686 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2888. Min Act: -0.0000

Data Index: 594009 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2862. Min Act: -0.0001

Data Index: 483527 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2732. Min Act: 0.0000

Data Index: 290667 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2693. Min Act: -0.0001

Data Index: 701045 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2700. Min Act: 0.0001

Data Index: 1005448 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2838. Min Act: -0.0000

Data Index: 902399 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2736. Min Act: -0.0000

Data Index: 230161 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2731. Min Act: -0.0001

Data Index: 455476 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.3850. Min Range: -0.3850

Max Act: 0.2731. Min Act: -0.0000

Data Index: 416639 (C4 (Web Text))

Max Activating Token Index: 437