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

Dataset: The Pile

Neuron 1628 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: 3.1558. Min Range: -3.1558

Max Act: 3.1558. Min Act: -0.0000

Data Index: 1728522 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.6213. Min Act: -0.0000

Data Index: 367240 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.3386. Min Act: -0.0000

Data Index: 867521 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.4456. Min Act: -0.0000

Data Index: 1530845 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.2868. Min Act: -0.0000

Data Index: 1220682 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.3319. Min Act: -0.0000

Data Index: 1338795 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.1217. Min Act: -0.0000

Data Index: 1978455 (The Pile)

Max Activating Token Index: 944

Text #7

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.1643. Min Act: -0.0000

Data Index: 1435485 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.1886. Min Act: -0.0000

Data Index: 959021 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.0509. Min Act: -0.0000

Data Index: 387225 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.9210. Min Act: -0.0000

Data Index: 1493866 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 3.1558. Min Range: -3.1558

Max Act: 2.0221. Min Act: -0.0000

Data Index: 976999 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.9845. Min Act: -0.0000

Data Index: 750303 (The Pile)

Max Activating Token Index: 276

Text #13

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.8759. Min Act: -0.0000

Data Index: 111270 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.8369. Min Act: -0.0000

Data Index: 564020 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.9964. Min Act: -0.0000

Data Index: 1598175 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.8746. Min Act: -0.0000

Data Index: 1228628 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.7953. Min Act: -0.0000

Data Index: 1049287 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.6349. Min Act: -0.0000

Data Index: 652545 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 3.1558. Min Range: -3.1558

Max Act: 1.8303. Min Act: -0.0000

Data Index: 506109 (The Pile)

Max Activating Token Index: 974