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

Dataset: The Pile

Neuron 3248 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3855. Min Range: -7.3855

Max Act: 7.3855. Min Act: -0.0000

Data Index: 196811 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 7.3855. Min Range: -7.3855

Max Act: 6.9688. Min Act: -0.0000

Data Index: 559635 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 7.3855. Min Range: -7.3855

Max Act: 6.6368. Min Act: -0.0000

Data Index: 1228453 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 7.3855. Min Range: -7.3855

Max Act: 7.0592. Min Act: -0.0000

Data Index: 1059756 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 7.3855. Min Range: -7.3855

Max Act: 6.6982. Min Act: -0.0000

Data Index: 646249 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.9288. Min Act: -0.0000

Data Index: 1331221 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.8164. Min Act: -0.0000

Data Index: 1006493 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 7.3855. Min Range: -7.3855

Max Act: 6.1535. Min Act: -0.0000

Data Index: 1178951 (The Pile)

Max Activating Token Index: 144

Text #8

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.9447. Min Act: -0.0000

Data Index: 213459 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.7832. Min Act: -0.0000

Data Index: 1204999 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.6756. Min Act: -0.0000

Data Index: 1644403 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 7.3855. Min Range: -7.3855

Max Act: 6.0295. Min Act: -0.0000

Data Index: 379662 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.9554. Min Act: -0.0000

Data Index: 603227 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.6838. Min Act: -0.0000

Data Index: 1738535 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.5250. Min Act: -0.0000

Data Index: 748518 (The Pile)

Max Activating Token Index: 115

Text #15

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.0933. Min Act: -0.0000

Data Index: 1547589 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.6630. Min Act: -0.0000

Data Index: 1984841 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.4638. Min Act: -0.0000

Data Index: 282975 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.3707. Min Act: -0.0000

Data Index: 1455764 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 7.3855. Min Range: -7.3855

Max Act: 5.2926. Min Act: -0.0000

Data Index: 1868763 (The Pile)

Max Activating Token Index: 366