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

Dataset: The Pile

Neuron 1369 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: 0.2702. Min Range: -0.2702

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1358478 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2266. Min Act: -0.0000

Data Index: 443953 (The Pile)

Max Activating Token Index: 912

Text #2

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1871021 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1827777 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2138. Min Act: -0.0000

Data Index: 115897 (The Pile)

Max Activating Token Index: 53

Text #5

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2054. Min Act: -0.0000

Data Index: 285423 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1399221 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1803665 (The Pile)

Max Activating Token Index: 267

Text #8

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1937026 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1889. Min Act: -0.0000

Data Index: 887375 (The Pile)

Max Activating Token Index: 59

Text #10

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1312495 (The Pile)

Max Activating Token Index: 268

Text #11

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1866. Min Act: -0.0000

Data Index: 467760 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1555219 (The Pile)

Max Activating Token Index: 314

Text #13

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1918. Min Act: -0.0000

Data Index: 225472 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1279384 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1867554 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1469188 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1943975 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1321153 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.2702. Min Range: -0.2702

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1793076 (The Pile)

Max Activating Token Index: 261