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

Dataset: The Pile

Neuron 2063 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1279008 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.4673. Min Act: -0.0000

Data Index: 27094 (The Pile)

Max Activating Token Index: 203

Text #2

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1246738 (The Pile)

Max Activating Token Index: 68

Text #3

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1913359 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3149. Min Act: -0.0000

Data Index: 373238 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2957. Min Act: -0.0000

Data Index: 1244282 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.3022. Min Act: -0.0000

Data Index: 393191 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2863. Min Act: -0.0000

Data Index: 642222 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2900. Min Act: -0.0000

Data Index: 244510 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1159335 (The Pile)

Max Activating Token Index: 125

Text #10

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2767. Min Act: -0.0000

Data Index: 41013 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1538736 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2752. Min Act: -0.0000

Data Index: 509451 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1347119 (The Pile)

Max Activating Token Index: 310

Text #14

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1513229 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1194408 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1411153 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1845151 (The Pile)

Max Activating Token Index: 823

Text #18

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2538. Min Act: -0.0000

Data Index: 216973 (The Pile)

Max Activating Token Index: 639

Text #19

Max Range: 0.6180. Min Range: -0.6180

Max Act: 0.2425. Min Act: -0.0000

Data Index: 916549 (The Pile)

Max Activating Token Index: 375