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

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

Neuron 4049 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: 0.6842. Min Range: -0.6842

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1198365 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4909. Min Act: -0.0000

Data Index: 455911 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4831. Min Act: -0.0000

Data Index: 495973 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4793. Min Act: -0.0000

Data Index: 243320 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1253561 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4560. Min Act: -0.0000

Data Index: 1210561 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4558. Min Act: -0.0000

Data Index: 643249 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4416. Min Act: -0.0000

Data Index: 534032 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4470. Min Act: -0.0000

Data Index: 335018 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4510. Min Act: -0.0000

Data Index: 91584 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1032898 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4290. Min Act: -0.0000

Data Index: 228061 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1177914 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4233. Min Act: -0.0000

Data Index: 692885 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4162. Min Act: -0.0000

Data Index: 441028 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4039. Min Act: 0.0000

Data Index: 680232 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4166. Min Act: 0.0000

Data Index: 146861 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4011. Min Act: -0.0000

Data Index: 713805 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1341592 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4039. Min Act: -0.0000

Data Index: 302576 (C4 (Web Text))

Max Activating Token Index: 688