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

Dataset: The Pile

Neuron 2611 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2209. Min Range: -7.2209

Max Act: 7.2209. Min Act: -0.0000

Data Index: 114848 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.9319. Min Act: -0.0000

Data Index: 1531070 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.5123. Min Act: -0.0000

Data Index: 1616154 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.2978. Min Act: -0.0000

Data Index: 1767260 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.2111. Min Act: -0.0000

Data Index: 448766 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.3741. Min Act: -0.0000

Data Index: 1402047 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.1060. Min Act: -0.0000

Data Index: 1488966 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.3214. Min Act: -0.0000

Data Index: 792804 (The Pile)

Max Activating Token Index: 862

Text #8

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.8869. Min Act: -0.0000

Data Index: 1187763 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.4566. Min Act: -0.0000

Data Index: 381957 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 7.2209. Min Range: -7.2209

Max Act: 6.1907. Min Act: -0.0000

Data Index: 1519317 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.7270. Min Act: -0.0000

Data Index: 1471709 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.6983. Min Act: -0.0000

Data Index: 750697 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.8571. Min Act: -0.0000

Data Index: 1571184 (The Pile)

Max Activating Token Index: 645

Text #14

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.9844. Min Act: -0.0000

Data Index: 705403 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.9774. Min Act: -0.0000

Data Index: 1672317 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.9546. Min Act: -0.0000

Data Index: 1682789 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.5518. Min Act: -0.0000

Data Index: 1902313 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.8953. Min Act: -0.0000

Data Index: 111142 (The Pile)

Max Activating Token Index: 343

Text #19

Max Range: 7.2209. Min Range: -7.2209

Max Act: 5.7007. Min Act: -0.0000

Data Index: 1079950 (The Pile)

Max Activating Token Index: 353