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

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

Neuron 2849 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.5860. Min Act: 0.0000

Data Index: 779249 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.4113. Min Act: -0.0000

Data Index: 150919 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 2.5860. Min Range: -2.5860

Max Act: 2.0050. Min Act: -0.0000

Data Index: 54210 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.8523. Min Act: -0.0000

Data Index: 45747 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.7495. Min Act: -0.0000

Data Index: 444692 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.6839. Min Act: -0.0000

Data Index: 493021 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.5355. Min Act: -0.0000

Data Index: 723632 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.5463. Min Act: -0.0000

Data Index: 609946 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.5709. Min Act: -0.0000

Data Index: 581044 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.5034. Min Act: -0.0000

Data Index: 169458 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.4486. Min Act: -0.0000

Data Index: 90205 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.4461. Min Act: -0.0000

Data Index: 274364 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1454 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.4094. Min Act: -0.0000

Data Index: 1160011 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.3968. Min Act: -0.0000

Data Index: 854146 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.2935. Min Act: -0.0000

Data Index: 435578 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.2880. Min Act: -0.0000

Data Index: 917326 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.3535. Min Act: -0.0000

Data Index: 317266 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.2766. Min Act: -0.0000

Data Index: 275035 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 2.5860. Min Range: -2.5860

Max Act: 1.3485. Min Act: -0.0000

Data Index: 963523 (C4 (Web Text))

Max Activating Token Index: 704