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

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

Neuron 3702 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: 1.5710. Min Range: -1.5710

Max Act: 1.5710. Min Act: -0.0000

Data Index: 378884 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1005705 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2431. Min Act: -0.0000

Data Index: 153546 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.4183. Min Act: -0.0000

Data Index: 147193 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1151818 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.2635. Min Act: -0.0000

Data Index: 950513 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.1465. Min Act: -0.0000

Data Index: 876652 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1101180 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.1875. Min Act: -0.0000

Data Index: 659535 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1218727 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.1832. Min Act: -0.0000

Data Index: 582331 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.1035. Min Act: -0.0000

Data Index: 911182 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1115990 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1085714 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.0474. Min Act: -0.0000

Data Index: 292062 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.0177. Min Act: -0.0000

Data Index: 303369 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.0326. Min Act: -0.0000

Data Index: 12544 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 1.5710. Min Range: -1.5710

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1345344 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 1.5710. Min Range: -1.5710

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1258518 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 1.5710. Min Range: -1.5710

Max Act: 0.9480. Min Act: -0.0000

Data Index: 739215 (C4 (Web Text))

Max Activating Token Index: 512