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

Dataset: The Pile

Neuron 3058 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.7576. Min Act: -0.0000

Data Index: 456181 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4276. Min Act: -0.0000

Data Index: 1485035 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4758. Min Act: -0.0000

Data Index: 1161643 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.3448. Min Act: -0.0000

Data Index: 72298 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.4201. Min Act: -0.0000

Data Index: 1757779 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.3212. Min Act: -0.0000

Data Index: 1812495 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1635. Min Act: -0.0000

Data Index: 714072 (The Pile)

Max Activating Token Index: 57

Text #7

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1919. Min Act: -0.0000

Data Index: 640193 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1726963 (The Pile)

Max Activating Token Index: 133

Text #9

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1543880 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1736. Min Act: -0.0000

Data Index: 62214 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.1271. Min Act: -0.0000

Data Index: 1676286 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0737. Min Act: -0.0000

Data Index: 784718 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1907556 (The Pile)

Max Activating Token Index: 511

Text #14

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0578. Min Act: -0.0000

Data Index: 586642 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0868. Min Act: -0.0000

Data Index: 700117 (The Pile)

Max Activating Token Index: 1020

Text #16

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0814. Min Act: -0.0000

Data Index: 440127 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0657. Min Act: -0.0000

Data Index: 398147 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1607208 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 1.7576. Min Range: -1.7576

Max Act: 1.0217. Min Act: -0.0000

Data Index: 1472586 (The Pile)

Max Activating Token Index: 447