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

Dataset: The Pile

Neuron 3489 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: 1.5889. Min Range: -1.5889

Max Act: 1.5889. Min Act: -0.0000

Data Index: 60715 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.4148. Min Act: -0.0000

Data Index: 1700513 (The Pile)

Max Activating Token Index: 40

Text #2

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1008470 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.4631. Min Act: -0.0000

Data Index: 1035836 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.4859. Min Act: -0.0000

Data Index: 1032235 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3264. Min Act: -0.0000

Data Index: 1705204 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3105. Min Act: -0.0000

Data Index: 450802 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1297221 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1881363 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3119. Min Act: -0.0000

Data Index: 106685 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2934. Min Act: -0.0000

Data Index: 852472 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3022. Min Act: -0.0000

Data Index: 1544527 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3095. Min Act: -0.0000

Data Index: 1012328 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1814964 (The Pile)

Max Activating Token Index: 998

Text #14

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.3338. Min Act: -0.0000

Data Index: 14950 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1532148 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2531. Min Act: -0.0000

Data Index: 127554 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.1859. Min Act: -0.0000

Data Index: 1985229 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1170321 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1298901 (The Pile)

Max Activating Token Index: 299