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

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

Neuron 1002 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6890. Min Act: -0.0000

Data Index: 975113 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6157. Min Act: -0.0000

Data Index: 61944 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1046684 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.6093. Min Act: -0.0000

Data Index: 644092 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5754. Min Act: -0.0000

Data Index: 338582 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5921. Min Act: -0.0000

Data Index: 462124 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1219670 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5454. Min Act: -0.0000

Data Index: 476434 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1333039 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5108. Min Act: -0.0000

Data Index: 355564 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1083863 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1216626 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4973. Min Act: -0.0000

Data Index: 569658 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4974. Min Act: -0.0000

Data Index: 343833 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5232. Min Act: -0.0000

Data Index: 2136 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1041145 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.4879. Min Act: -0.0000

Data Index: 825512 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1074921 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5027. Min Act: -0.0000

Data Index: 52471 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.6890. Min Range: -0.6890

Max Act: 0.5019. Min Act: -0.0000

Data Index: 396754 (C4 (Web Text))

Max Activating Token Index: 128