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

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

Neuron 234 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: 0.4332. Min Range: -0.4332

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1052428 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1608156 (Python Code)

Max Activating Token Index: 845

Text #2

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.4169. Min Act: -0.0000

Data Index: 562972 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1339600 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3800. Min Act: -0.0000

Data Index: 782984 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1447629 (Python Code)

Max Activating Token Index: 693

Text #6

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3906. Min Act: -0.0000

Data Index: 61875 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3790. Min Act: -0.0000

Data Index: 345912 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3464. Min Act: -0.0000

Data Index: 788562 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1094005 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1575709 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1446675 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3866. Min Act: -0.0000

Data Index: 203548 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3817. Min Act: -0.0000

Data Index: 59960 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3424. Min Act: -0.0000

Data Index: 43023 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3582. Min Act: -0.0000

Data Index: 597583 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1384019 (Python Code)

Max Activating Token Index: 975

Text #17

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1585070 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1324601 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.4332. Min Range: -0.4332

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1616989 (Python Code)

Max Activating Token Index: 793