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

Dataset: The Pile

Neuron 92 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: 3.3898. Min Range: -3.3898

Max Act: 3.3898. Min Act: -0.0000

Data Index: 1475943 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2799. Min Act: -0.0000

Data Index: 1109804 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2547. Min Act: -0.0000

Data Index: 1172444 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2095. Min Act: -0.0000

Data Index: 1227769 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.1967. Min Act: -0.0000

Data Index: 645540 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.0759. Min Act: -0.0000

Data Index: 1549054 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 3.3898. Min Range: -3.3898

Max Act: 2.9220. Min Act: -0.0000

Data Index: 192507 (The Pile)

Max Activating Token Index: 71

Text #7

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.1959. Min Act: -0.0000

Data Index: 1489939 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 3.3898. Min Range: -3.3898

Max Act: 2.8939. Min Act: -0.0000

Data Index: 146448 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.1946. Min Act: -0.0000

Data Index: 1647387 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.1966. Min Act: -0.0000

Data Index: 448257 (The Pile)

Max Activating Token Index: 99

Text #11

Max Range: 3.3898. Min Range: -3.3898

Max Act: 2.7455. Min Act: -0.0000

Data Index: 1502304 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.0306. Min Act: -0.0000

Data Index: 307616 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.0314. Min Act: -0.0000

Data Index: 788868 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.1720. Min Act: -0.0000

Data Index: 520961 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 3.3898. Min Range: -3.3898

Max Act: 2.7503. Min Act: -0.0000

Data Index: 1724756 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.2809. Min Act: -0.0000

Data Index: 329946 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.1770. Min Act: -0.0000

Data Index: 1490480 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.1427. Min Act: -0.0000

Data Index: 54071 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 3.3898. Min Range: -3.3898

Max Act: 3.0050. Min Act: -0.0000

Data Index: 407956 (The Pile)

Max Activating Token Index: 90