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

Dataset: The Pile

Neuron 2076 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9650. Min Range: -7.9650

Max Act: 7.9650. Min Act: -0.0000

Data Index: 1266103 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.8680. Min Act: -0.0000

Data Index: 1666171 (The Pile)

Max Activating Token Index: 149

Text #2

Max Range: 7.9650. Min Range: -7.9650

Max Act: 7.0104. Min Act: -0.0000

Data Index: 1671457 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.7309. Min Act: -0.0000

Data Index: 7101 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.6612. Min Act: -0.0000

Data Index: 156743 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.9070. Min Act: -0.0000

Data Index: 500337 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.6737. Min Act: -0.0000

Data Index: 136361 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.8761. Min Act: -0.0000

Data Index: 1314850 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.3740. Min Act: -0.0000

Data Index: 1541050 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.3989. Min Act: -0.0000

Data Index: 705508 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.3521. Min Act: -0.0000

Data Index: 1275821 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.4414. Min Act: -0.0000

Data Index: 219500 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.4259. Min Act: -0.0000

Data Index: 636865 (The Pile)

Max Activating Token Index: 263

Text #13

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.5322. Min Act: -0.0000

Data Index: 1315077 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.7139. Min Act: -0.0000

Data Index: 1531268 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.0269. Min Act: -0.0000

Data Index: 631378 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.0580. Min Act: -0.0000

Data Index: 1336051 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 7.9650. Min Range: -7.9650

Max Act: 5.9933. Min Act: -0.0000

Data Index: 662870 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.1708. Min Act: -0.0000

Data Index: 182838 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 7.9650. Min Range: -7.9650

Max Act: 6.7265. Min Act: -0.0000

Data Index: 1322678 (The Pile)

Max Activating Token Index: 907