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

Dataset: The Pile

Neuron 4238 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: 1.1971. Min Range: -1.1971

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1042611 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0948. Min Act: -0.0000

Data Index: 500507 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1476. Min Act: -0.0000

Data Index: 1069705 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.1077. Min Act: -0.0000

Data Index: 1069939 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1941754 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1227002 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0095. Min Act: -0.0000

Data Index: 688527 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 1.1971. Min Range: -1.1971

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1242170 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1677159 (The Pile)

Max Activating Token Index: 382

Text #9

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1216105 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1700056 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9288. Min Act: -0.0000

Data Index: 1903444 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1327634 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9358. Min Act: -0.0000

Data Index: 315184 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1108906 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1801892 (The Pile)

Max Activating Token Index: 148

Text #16

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9057. Min Act: -0.0000

Data Index: 862255 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1535406 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.8619. Min Act: -0.0000

Data Index: 61746 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 1.1971. Min Range: -1.1971

Max Act: 0.9132. Min Act: -0.0000

Data Index: 892651 (The Pile)

Max Activating Token Index: 81