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

Dataset: The Pile

Neuron 4794 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: 0.4872. Min Range: -0.4872

Max Act: 0.4872. Min Act: -0.0000

Data Index: 39151 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1810541 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1128405 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1698339 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3616. Min Act: -0.0000

Data Index: 57312 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3394. Min Act: -0.0000

Data Index: 138954 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1189811 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3061. Min Act: -0.0000

Data Index: 106790 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1715433 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1623042 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3178. Min Act: -0.0000

Data Index: 482575 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1599203 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3012. Min Act: -0.0000

Data Index: 124332 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.3190. Min Act: -0.0000

Data Index: 911422 (The Pile)

Max Activating Token Index: 949

Text #14

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.2969. Min Act: -0.0000

Data Index: 355290 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.2832. Min Act: -0.0000

Data Index: 500138 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.2886. Min Act: -0.0000

Data Index: 797263 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.2804. Min Act: -0.0000

Data Index: 509968 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1456097 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.4872. Min Range: -0.4872

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1415470 (The Pile)

Max Activating Token Index: 378