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

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

Neuron 93 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1054279 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1256860 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6394. Min Act: -0.0001

Data Index: 129042 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6759. Min Act: -0.0001

Data Index: 1255439 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1211300 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1192675 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6381. Min Act: -0.0001

Data Index: 953204 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6417. Min Act: -0.0001

Data Index: 264062 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5979. Min Act: -0.0000

Data Index: 572543 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6099. Min Act: -0.0001

Data Index: 229498 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6270. Min Act: -0.0001

Data Index: 1132552 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5661. Min Act: -0.0001

Data Index: 534931 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6349. Min Act: -0.0001

Data Index: 864303 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6362. Min Act: -0.0000

Data Index: 971205 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5954. Min Act: -0.0001

Data Index: 1226557 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1174204 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1337734 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5817. Min Act: -0.0001

Data Index: 898288 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1248851 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.7259. Min Range: -0.7259

Max Act: 0.5599. Min Act: -0.0001

Data Index: 662936 (C4 (Web Text))

Max Activating Token Index: 445