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

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

Neuron 982 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1775. Min Range: -2.1775

Max Act: 2.1775. Min Act: -0.0000

Data Index: 431919 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4898. Min Act: -0.0000

Data Index: 673246 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.7032. Min Act: -0.0000

Data Index: 642682 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4875. Min Act: -0.0000

Data Index: 840542 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.5684. Min Act: -0.0000

Data Index: 1016786 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.5833. Min Act: -0.0000

Data Index: 31811 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4866. Min Act: -0.0000

Data Index: 241304 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4490. Min Act: -0.0000

Data Index: 1316058 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4612. Min Act: -0.0000

Data Index: 1031940 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3729. Min Act: -0.0000

Data Index: 532170 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4428. Min Act: -0.0000

Data Index: 494183 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3653. Min Act: -0.0000

Data Index: 662666 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1086487 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3886. Min Act: -0.0000

Data Index: 651604 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3958. Min Act: -0.0000

Data Index: 669921 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1208523 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.2936. Min Act: -0.0000

Data Index: 450628 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.3124. Min Act: -0.0000

Data Index: 294569 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.4257. Min Act: -0.0000

Data Index: 850982 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 2.1775. Min Range: -2.1775

Max Act: 1.2519. Min Act: -0.0000

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 125