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

Dataset: The Pile

Neuron 3422 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.2148. Min Act: -0.0000

Data Index: 98658 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1104625 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1675106 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1868733 (The Pile)

Max Activating Token Index: 92

Text #4

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9861. Min Act: -0.0000

Data Index: 825386 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1812090 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0719. Min Act: -0.0000

Data Index: 147888 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8574. Min Act: -0.0000

Data Index: 31939 (The Pile)

Max Activating Token Index: 199

Text #8

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9292. Min Act: -0.0000

Data Index: 208202 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0452. Min Act: -0.0000

Data Index: 30982 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1748838 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1145702 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1496671 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1137067 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.9582. Min Act: -0.0000

Data Index: 523337 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1240968 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1156578 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 1.2148. Min Range: -1.2148

Max Act: 1.0161. Min Act: -0.0000

Data Index: 467876 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.7622. Min Act: -0.0000

Data Index: 641705 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 1.2148. Min Range: -1.2148

Max Act: 0.8068. Min Act: -0.0000

Data Index: 443056 (The Pile)

Max Activating Token Index: 921