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

Dataset: The Pile

Neuron 4340 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.4137. Min Act: -0.0000

Data Index: 927063 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.3277. Min Act: -0.0000

Data Index: 466447 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1326. Min Act: -0.0000

Data Index: 7430 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1182. Min Act: -0.0000

Data Index: 1335500 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0527. Min Act: -0.0000

Data Index: 264297 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.1156. Min Act: -0.0000

Data Index: 70359 (The Pile)

Max Activating Token Index: 509

Text #6

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8801. Min Act: -0.0000

Data Index: 735182 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9668. Min Act: -0.0000

Data Index: 730956 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.7750. Min Act: -0.0000

Data Index: 158793 (The Pile)

Max Activating Token Index: 898

Text #9

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8859. Min Act: -0.0000

Data Index: 75474 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1262798 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1345147 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1244610 (The Pile)

Max Activating Token Index: 833

Text #13

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1559817 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8412. Min Act: -0.0000

Data Index: 51543 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 1.4137. Min Range: -1.4137

Max Act: 1.0580. Min Act: -0.0000

Data Index: 582382 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1643507 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1962057 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8883. Min Act: -0.0000

Data Index: 604665 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 1.4137. Min Range: -1.4137

Max Act: 0.8543. Min Act: -0.0000

Data Index: 1891483 (The Pile)

Max Activating Token Index: 665