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

Dataset: The Pile

Neuron 1393 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.4091. Min Act: -0.0000

Data Index: 264358 (The Pile)

Max Activating Token Index: 137

Text #1

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1884935 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1906051 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3458. Min Act: -0.0000

Data Index: 263200 (The Pile)

Max Activating Token Index: 125

Text #4

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1318216 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1527926 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3241. Min Act: -0.0000

Data Index: 210676 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3473. Min Act: -0.0000

Data Index: 1287038 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1412366 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2933. Min Act: -0.0000

Data Index: 171559 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3005. Min Act: -0.0000

Data Index: 69156 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1773819 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1615902 (The Pile)

Max Activating Token Index: 326

Text #13

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1832040 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1179369 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2919. Min Act: -0.0000

Data Index: 351738 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2910. Min Act: -0.0000

Data Index: 451496 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.3002. Min Act: -0.0000

Data Index: 237793 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1486549 (The Pile)

Max Activating Token Index: 823

Text #19

Max Range: 0.4103. Min Range: -0.4103

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1252852 (The Pile)

Max Activating Token Index: 146