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

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

Neuron 4465 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: 0.7315. Min Range: -0.7315

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1217935 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1242308 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.6367. Min Act: -0.0000

Data Index: 902599 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1244989 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4803. Min Act: -0.0000

Data Index: 170878 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.5081. Min Act: -0.0000

Data Index: 508469 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1252575 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.5130. Min Act: -0.0000

Data Index: 62110 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.5063. Min Act: -0.0000

Data Index: 677622 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1242589 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.5062. Min Act: -0.0000

Data Index: 74165 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4877. Min Act: -0.0000

Data Index: 178056 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1304960 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4774. Min Act: -0.0000

Data Index: 492240 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4742. Min Act: -0.0000

Data Index: 40982 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4912. Min Act: -0.0000

Data Index: 516575 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4682. Min Act: -0.0000

Data Index: 426547 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4681. Min Act: -0.0000

Data Index: 561020 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4821. Min Act: -0.0000

Data Index: 589024 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.7315. Min Range: -0.7315

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1339565 (C4 (Web Text))

Max Activating Token Index: 791