Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1776 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.9915. Min Act: -0.0001

Data Index: 22725 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8987. Min Act: -0.0001

Data Index: 175379 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8496. Min Act: -0.0001

Data Index: 140272 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8078. Min Act: -0.0001

Data Index: 548201 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8054. Min Act: -0.0001

Data Index: 467952 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8320. Min Act: -0.0001

Data Index: 814356 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8278. Min Act: -0.0001

Data Index: 74057 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8170. Min Act: -0.0001

Data Index: 1130671 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7867. Min Act: -0.0001

Data Index: 1156198 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7644. Min Act: -0.0001

Data Index: 1345347 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7875. Min Act: -0.0001

Data Index: 202257 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7794. Min Act: -0.0001

Data Index: 30930 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7999. Min Act: -0.0001

Data Index: 983617 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7517. Min Act: -0.0001

Data Index: 14040 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8485. Min Act: -0.0001

Data Index: 26629 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7869. Min Act: -0.0001

Data Index: 141133 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7161. Min Act: -0.0001

Data Index: 1118606 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7943. Min Act: -0.0001

Data Index: 88226 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8333. Min Act: -0.0001

Data Index: 1295145 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7796. Min Act: -0.0001

Data Index: 99515 (C4 (Web Text))

Max Activating Token Index: 502