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

Dataset: The Pile

Neuron 3152 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: 0.8039. Min Range: -0.8039

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1087995 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.8039. Min Act: -0.0000

Data Index: 845173 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.7230. Min Act: -0.0000

Data Index: 743819 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1178061 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1434673 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6834. Min Act: -0.0000

Data Index: 200228 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1505156 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1855465 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1151410 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6696. Min Act: -0.0000

Data Index: 503747 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1999121 (The Pile)

Max Activating Token Index: 194

Text #11

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1999447 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6972. Min Act: -0.0000

Data Index: 692618 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1884156 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.7194. Min Act: -0.0000

Data Index: 221420 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1335325 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1757982 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.5999. Min Act: -0.0000

Data Index: 177095 (The Pile)

Max Activating Token Index: 677

Text #18

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6311. Min Act: -0.0000

Data Index: 406751 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 0.8039. Min Range: -0.8039

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1752894 (The Pile)

Max Activating Token Index: 165