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

Dataset: The Pile

Neuron 1756 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.7187. Min Act: -0.0000

Data Index: 663770 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5586. Min Act: -0.0000

Data Index: 279536 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5648. Min Act: -0.0000

Data Index: 1306079 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1842883 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5407. Min Act: -0.0000

Data Index: 1550870 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.5320. Min Act: -0.0000

Data Index: 423649 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4988. Min Act: -0.0000

Data Index: 56805 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4779. Min Act: -0.0000

Data Index: 1176949 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1889343 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4176. Min Act: -0.0000

Data Index: 848661 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3995. Min Act: -0.0000

Data Index: 383854 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3073. Min Act: -0.0000

Data Index: 146266 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.2828. Min Act: -0.0000

Data Index: 262422 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1373679 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1187688 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1248425 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3547. Min Act: -0.0000

Data Index: 1559744 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1822380 (The Pile)

Max Activating Token Index: 701

Text #18

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.2647. Min Act: -0.0000

Data Index: 500982 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 1.7187. Min Range: -1.7187

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1730072 (The Pile)

Max Activating Token Index: 7