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

Dataset: The Pile

Neuron 3058 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: 5.0931. Min Range: -5.0931

Max Act: 5.0931. Min Act: -0.0000

Data Index: 904006 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 5.0931. Min Range: -5.0931

Max Act: 4.3052. Min Act: -0.0000

Data Index: 393768 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 5.0931. Min Range: -5.0931

Max Act: 3.1549. Min Act: -0.0000

Data Index: 1903028 (The Pile)

Max Activating Token Index: 685

Text #3

Max Range: 5.0931. Min Range: -5.0931

Max Act: 3.0484. Min Act: -0.0000

Data Index: 1950435 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 5.0931. Min Range: -5.0931

Max Act: 3.1356. Min Act: -0.0000

Data Index: 694454 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.9752. Min Act: -0.0000

Data Index: 80061 (The Pile)

Max Activating Token Index: 473

Text #6

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.8891. Min Act: -0.0000

Data Index: 561334 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.9078. Min Act: -0.0000

Data Index: 810457 (The Pile)

Max Activating Token Index: 496

Text #8

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.8868. Min Act: -0.0000

Data Index: 1492435 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.8573. Min Act: -0.0000

Data Index: 375831 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.5502. Min Act: -0.0000

Data Index: 39727 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.5858. Min Act: -0.0000

Data Index: 1748867 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.7206. Min Act: -0.0000

Data Index: 1439000 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.4983. Min Act: -0.0000

Data Index: 735417 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.3943. Min Act: -0.0000

Data Index: 1278217 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.4386. Min Act: -0.0000

Data Index: 1401449 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.2562. Min Act: -0.0000

Data Index: 1175431 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.4598. Min Act: -0.0000

Data Index: 1329012 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.3234. Min Act: -0.0000

Data Index: 1903368 (The Pile)

Max Activating Token Index: 340

Text #19

Max Range: 5.0931. Min Range: -5.0931

Max Act: 2.2301. Min Act: -0.0000

Data Index: 17078 (The Pile)

Max Activating Token Index: 798