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

Dataset: The Pile

Neuron 3855 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: 1.5134. Min Range: -1.5134

Max Act: 1.5134. Min Act: -0.0000

Data Index: 466803 (The Pile)

Max Activating Token Index: 330

Text #1

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2564. Min Act: -0.0000

Data Index: 310771 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2214. Min Act: -0.0000

Data Index: 422769 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1424998 (The Pile)

Max Activating Token Index: 305

Text #4

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2910. Min Act: -0.0000

Data Index: 320618 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2801. Min Act: -0.0000

Data Index: 456148 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2107. Min Act: -0.0000

Data Index: 586509 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1885. Min Act: -0.0000

Data Index: 18243 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2340. Min Act: -0.0000

Data Index: 106985 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1961511 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1947338 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2088. Min Act: -0.0000

Data Index: 740719 (The Pile)

Max Activating Token Index: 784

Text #12

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1773570 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1921. Min Act: -0.0000

Data Index: 273452 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1556. Min Act: -0.0000

Data Index: 14105 (The Pile)

Max Activating Token Index: 553

Text #15

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1997098 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1088738 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.0930. Min Act: -0.0000

Data Index: 487960 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1274. Min Act: -0.0000

Data Index: 723642 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 1.5134. Min Range: -1.5134

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1164645 (The Pile)

Max Activating Token Index: 41