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

Dataset: The Pile

Neuron 2106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1054396 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0557. Min Act: -0.0000

Data Index: 358489 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1209236 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 1.2177. Min Range: -1.2177

Max Act: 0.8882. Min Act: -0.0000

Data Index: 1410336 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1948451 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1511774 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.1125. Min Act: -0.0000

Data Index: 1851231 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 1.2177. Min Range: -1.2177

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1553026 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 1.2177. Min Range: -1.2177

Max Act: 0.9588. Min Act: -0.0000

Data Index: 566029 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1639743 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.1000. Min Act: -0.0000

Data Index: 67514 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0938. Min Act: -0.0000

Data Index: 329684 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.1097. Min Act: -0.0000

Data Index: 934086 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1601320 (The Pile)

Max Activating Token Index: 135

Text #14

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1168477 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1375270 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0519. Min Act: -0.0000

Data Index: 1278722 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 1.2177. Min Range: -1.2177

Max Act: 0.9783. Min Act: -0.0000

Data Index: 53584 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1551648 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 1.2177. Min Range: -1.2177

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1295608 (The Pile)

Max Activating Token Index: 185