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

Dataset: The Pile

Neuron 788 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: 0.7365. Min Range: -0.7365

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1503166 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1661075 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1397994 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1561103 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1445033 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6888. Min Act: -0.0000

Data Index: 299262 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6725. Min Act: -0.0000

Data Index: 535619 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6399. Min Act: -0.0000

Data Index: 457715 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6291. Min Act: -0.0000

Data Index: 438470 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6070. Min Act: -0.0000

Data Index: 667391 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1286115 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1224179 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1077733 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1281206 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1331360 (The Pile)

Max Activating Token Index: 307

Text #15

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6107. Min Act: -0.0000

Data Index: 1817742 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1924040 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6054. Min Act: -0.0000

Data Index: 219862 (The Pile)

Max Activating Token Index: 74

Text #18

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1651459 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.5824. Min Act: -0.0000

Data Index: 955142 (The Pile)

Max Activating Token Index: 522