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

Dataset: The Pile

Neuron 4213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1388050 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.0930. Min Act: -0.0000

Data Index: 411089 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 1.4213. Min Range: -1.4213

Max Act: 1.1320. Min Act: -0.0000

Data Index: 1356531 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9679. Min Act: -0.0000

Data Index: 178855 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9308. Min Act: -0.0000

Data Index: 303581 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1220891 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1541700 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9080. Min Act: -0.0000

Data Index: 614507 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9102. Min Act: -0.0000

Data Index: 1501046 (The Pile)

Max Activating Token Index: 558

Text #9

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1486927 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1092532 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1482890 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1993757 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1670175 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8197. Min Act: -0.0000

Data Index: 229695 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1559272 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8979. Min Act: -0.0000

Data Index: 508283 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1153694 (The Pile)

Max Activating Token Index: 537

Text #18

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8008. Min Act: -0.0000

Data Index: 191475 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 1.4213. Min Range: -1.4213

Max Act: 0.8233. Min Act: -0.0000

Data Index: 143354 (The Pile)

Max Activating Token Index: 887