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

Dataset: The Pile

Neuron 207 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1878915 (The Pile)

Max Activating Token Index: 507

Text #1

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.7288. Min Act: -0.0000

Data Index: 1325082 (The Pile)

Max Activating Token Index: 823

Text #2

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.6557. Min Act: -0.0000

Data Index: 1797478 (The Pile)

Max Activating Token Index: 889

Text #3

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.6217. Min Act: -0.0000

Data Index: 109485 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.5030. Min Act: -0.0000

Data Index: 1814689 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.5607. Min Act: -0.0000

Data Index: 1966482 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.4371. Min Act: -0.0000

Data Index: 1740117 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.5000. Min Act: -0.0000

Data Index: 905904 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1209445 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.4763. Min Act: -0.0000

Data Index: 512125 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1317203 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.5423. Min Act: -0.0000

Data Index: 1783598 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.4165. Min Act: -0.0000

Data Index: 762060 (The Pile)

Max Activating Token Index: 671

Text #13

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.3872. Min Act: -0.0000

Data Index: 164040 (The Pile)

Max Activating Token Index: 498

Text #14

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1419935 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.3366. Min Act: -0.0000

Data Index: 670147 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.3658. Min Act: -0.0000

Data Index: 1304778 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.3033. Min Act: -0.0000

Data Index: 1752393 (The Pile)

Max Activating Token Index: 902

Text #18

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.3442. Min Act: -0.0000

Data Index: 767238 (The Pile)

Max Activating Token Index: 987

Text #19

Max Range: 1.8076. Min Range: -1.8076

Max Act: 1.4161. Min Act: -0.0000

Data Index: 757255 (The Pile)

Max Activating Token Index: 478