Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1336 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1138. Min Range: -1.1138

Max Act: 1.1138. Min Act: -0.0000

Data Index: 296262 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1162290 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1545381 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1970846 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.4915. Min Act: -0.0000

Data Index: 632693 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1379052 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1675301 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1400214 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1557618 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1926676 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5155. Min Act: -0.0000

Data Index: 802153 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1104630 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1861777 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1742064 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.4233. Min Act: -0.0000

Data Index: 265905 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.3941. Min Act: -0.0000

Data Index: 275504 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1329506 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1902089 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1212612 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.1138. Min Range: -1.1138

Max Act: 0.4055. Min Act: -0.0000

Data Index: 311550 (The Pile)

Max Activating Token Index: 920