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

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

Neuron 3534 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: 2.8825. Min Range: -2.8825

Max Act: 2.8825. Min Act: -0.0000

Data Index: 1350691 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.5459. Min Act: -0.0000

Data Index: 330538 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.4909. Min Act: 0.0000

Data Index: 262772 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.4770. Min Act: -0.0000

Data Index: 1350128 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.2919. Min Act: -0.0000

Data Index: 319964 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.3811. Min Act: -0.0000

Data Index: 532537 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.3492. Min Act: 0.0000

Data Index: 681633 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.4046. Min Act: 0.0000

Data Index: 1094335 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1255398 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.2065. Min Act: -0.0000

Data Index: 394449 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.1939. Min Act: 0.0000

Data Index: 249682 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.1752. Min Act: -0.0000

Data Index: 510116 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.0411. Min Act: -0.0000

Data Index: 259381 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.1601. Min Act: -0.0000

Data Index: 813383 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.0528. Min Act: 0.0000

Data Index: 407869 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.1604. Min Act: -0.0000

Data Index: 325236 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.0147. Min Act: 0.0000

Data Index: 755852 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.2379. Min Act: -0.0000

Data Index: 1214597 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 2.8825. Min Range: -2.8825

Max Act: 2.0908. Min Act: -0.0000

Data Index: 21194 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 2.8825. Min Range: -2.8825

Max Act: 1.9470. Min Act: 0.0001

Data Index: 126402 (C4 (Web Text))

Max Activating Token Index: 463