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

Dataset: The Pile

Neuron 3810 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: 0.8770. Min Range: -0.8770

Max Act: 0.8770. Min Act: -0.0000

Data Index: 699731 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1615304 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1853232 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1977208 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1321644 (The Pile)

Max Activating Token Index: 673

Text #5

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7984. Min Act: -0.0000

Data Index: 241157 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7681. Min Act: -0.0000

Data Index: 859427 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7962. Min Act: -0.0000

Data Index: 146552 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1007405 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7368. Min Act: -0.0000

Data Index: 313186 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7432. Min Act: -0.0000

Data Index: 349407 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7681. Min Act: -0.0000

Data Index: 352117 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7322. Min Act: -0.0000

Data Index: 134252 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1213512 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1071642 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1149654 (The Pile)

Max Activating Token Index: 372

Text #16

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7869. Min Act: -0.0000

Data Index: 721198 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1058444 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7137. Min Act: -0.0000

Data Index: 231380 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 0.8770. Min Range: -0.8770

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1878238 (The Pile)

Max Activating Token Index: 236