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

Dataset: The Pile

Neuron 2816 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: 1.3045. Min Range: -1.3045

Max Act: 1.3045. Min Act: -0.0000

Data Index: 943499 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1308231 (The Pile)

Max Activating Token Index: 145

Text #2

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.1065. Min Act: -0.0000

Data Index: 525864 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.1629. Min Act: -0.0000

Data Index: 596343 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.1482. Min Act: -0.0000

Data Index: 1254749 (The Pile)

Max Activating Token Index: 645

Text #5

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0788. Min Act: -0.0000

Data Index: 999303 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9994. Min Act: -0.0000

Data Index: 1935303 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1589365 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9825. Min Act: -0.0000

Data Index: 820416 (The Pile)

Max Activating Token Index: 177

Text #9

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0103. Min Act: -0.0000

Data Index: 255844 (The Pile)

Max Activating Token Index: 918

Text #10

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1871822 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9583. Min Act: -0.0000

Data Index: 761573 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0404. Min Act: -0.0000

Data Index: 698728 (The Pile)

Max Activating Token Index: 364

Text #13

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9920. Min Act: -0.0000

Data Index: 967754 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1910356 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0217. Min Act: -0.0000

Data Index: 28142 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1649876 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1777390 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.3045. Min Range: -1.3045

Max Act: 0.9134. Min Act: -0.0000

Data Index: 963978 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 1.3045. Min Range: -1.3045

Max Act: 1.0287. Min Act: -0.0000

Data Index: 423799 (The Pile)

Max Activating Token Index: 145