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

Dataset: The Pile

Neuron 3043 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: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0000

Data Index: 17029 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1962604 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1263. Min Act: -0.0000

Data Index: 502974 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1025290 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1791145 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1572692 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1087. Min Act: -0.0000

Data Index: 883684 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1429184 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1082. Min Act: -0.0000

Data Index: 145344 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1114. Min Act: -0.0000

Data Index: 405269 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1031. Min Act: -0.0000

Data Index: 499377 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1052. Min Act: 0.0000

Data Index: 807648 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1052. Min Act: -0.0000

Data Index: 704489 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1628445 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1042. Min Act: -0.0000

Data Index: 56333 (The Pile)

Max Activating Token Index: 257

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1198251 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1054. Min Act: -0.0000

Data Index: 285342 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1090. Min Act: -0.0000

Data Index: 504158 (The Pile)

Max Activating Token Index: 418

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1007. Min Act: -0.0000

Data Index: 789453 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1095. Min Act: -0.0000

Data Index: 119651 (The Pile)

Max Activating Token Index: 823