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

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

Neuron 3289 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: 0.6557. Min Range: -0.6557

Max Act: 0.6557. Min Act: -0.0000

Data Index: 809673 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4277. Min Act: -0.0000

Data Index: 807926 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1060477 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4996. Min Act: -0.0000

Data Index: 569681 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1320041 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3973. Min Act: -0.0000

Data Index: 831898 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4065. Min Act: -0.0000

Data Index: 516689 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3958. Min Act: -0.0000

Data Index: 271844 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4062. Min Act: -0.0000

Data Index: 801689 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4044. Min Act: -0.0000

Data Index: 604419 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3787. Min Act: -0.0000

Data Index: 764797 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3753. Min Act: -0.0000

Data Index: 868212 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3985. Min Act: -0.0000

Data Index: 934126 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1062033 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1031609 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3680. Min Act: -0.0000

Data Index: 191587 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1266501 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3887. Min Act: -0.0000

Data Index: 437548 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3829. Min Act: -0.0000

Data Index: 786210 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1184187 (C4 (Web Text))

Max Activating Token Index: 164