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

Dataset: The Pile

Neuron 3287 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: 0.3162. Min Range: -0.3162

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1574451 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2750. Min Act: -0.0000

Data Index: 1742931 (The Pile)

Max Activating Token Index: 143

Text #2

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2314. Min Act: -0.0000

Data Index: 499314 (The Pile)

Max Activating Token Index: 218

Text #3

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1553596 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2375. Min Act: -0.0000

Data Index: 298186 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2449. Min Act: -0.0000

Data Index: 939791 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2325. Min Act: -0.0000

Data Index: 683899 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2089. Min Act: -0.0000

Data Index: 760127 (The Pile)

Max Activating Token Index: 351

Text #8

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1867048 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2067. Min Act: -0.0000

Data Index: 236602 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1881456 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2111. Min Act: -0.0000

Data Index: 147218 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1258534 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.2134. Min Act: -0.0000

Data Index: 356655 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1929. Min Act: -0.0000

Data Index: 1353267 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1871743 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1904. Min Act: -0.0000

Data Index: 108884 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1962. Min Act: -0.0000

Data Index: 811735 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1023351 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.3162. Min Range: -0.3162

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1870311 (The Pile)

Max Activating Token Index: 780