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

Dataset: The Pile

Neuron 200 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: 5.1893. Min Range: -5.1893

Max Act: 5.1893. Min Act: -0.0000

Data Index: 996446 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 5.1893. Min Range: -5.1893

Max Act: 4.4659. Min Act: -0.0000

Data Index: 191182 (The Pile)

Max Activating Token Index: 777

Text #2

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.5301. Min Act: -0.0000

Data Index: 1414485 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 5.1893. Min Range: -5.1893

Max Act: 4.2163. Min Act: -0.0000

Data Index: 512463 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.7300. Min Act: -0.0000

Data Index: 958256 (The Pile)

Max Activating Token Index: 1001

Text #5

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.7799. Min Act: -0.0000

Data Index: 403218 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.4613. Min Act: -0.0000

Data Index: 1047175 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.8982. Min Act: -0.0000

Data Index: 1547641 (The Pile)

Max Activating Token Index: 55

Text #8

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.7387. Min Act: -0.0000

Data Index: 1440919 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 5.1893. Min Range: -5.1893

Max Act: 4.3663. Min Act: -0.0000

Data Index: 62798 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.6834. Min Act: -0.0000

Data Index: 883211 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.6895. Min Act: -0.0000

Data Index: 1354166 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.2293. Min Act: -0.0000

Data Index: 929920 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.3168. Min Act: -0.0000

Data Index: 1193567 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.7955. Min Act: -0.0000

Data Index: 185834 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 5.1893. Min Range: -5.1893

Max Act: 4.0866. Min Act: -0.0000

Data Index: 1700677 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.6365. Min Act: -0.0000

Data Index: 1141729 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.4574. Min Act: -0.0000

Data Index: 1531765 (The Pile)

Max Activating Token Index: 489

Text #18

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.6160. Min Act: -0.0000

Data Index: 1548705 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 5.1893. Min Range: -5.1893

Max Act: 3.7284. Min Act: -0.0000

Data Index: 1122720 (The Pile)

Max Activating Token Index: 795