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

Dataset: The Pile

Neuron 5020 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: 0.2740. Min Range: -0.2740

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1103519 (The Pile)

Max Activating Token Index: 331

Text #1

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1192731 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2231. Min Act: -0.0000

Data Index: 529938 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1342516 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2296. Min Act: -0.0000

Data Index: 272144 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1408636 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2106. Min Act: -0.0000

Data Index: 531562 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2128. Min Act: -0.0000

Data Index: 703725 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2169. Min Act: -0.0000

Data Index: 951879 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1130147 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1956. Min Act: -0.0000

Data Index: 875150 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1991. Min Act: -0.0000

Data Index: 967543 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1288496 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1616066 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1792. Min Act: -0.0000

Data Index: 290059 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1841. Min Act: -0.0000

Data Index: 236219 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1437330 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1822. Min Act: -0.0000

Data Index: 780988 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1483004 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.2740. Min Range: -0.2740

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1245345 (The Pile)

Max Activating Token Index: 897