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

Dataset: The Pile

Neuron 2104 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.5834. Min Act: -0.0000

Data Index: 1601644 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.3189. Min Act: -0.0000

Data Index: 714694 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1294753 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.1894. Min Act: -0.0000

Data Index: 916736 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.0735. Min Act: -0.0000

Data Index: 862353 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.2280. Min Act: -0.0000

Data Index: 1490816 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.1297. Min Act: -0.0000

Data Index: 594777 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.0142. Min Act: -0.0000

Data Index: 1116739 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.1022. Min Act: -0.0000

Data Index: 973915 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.0699. Min Act: -0.0000

Data Index: 218437 (The Pile)

Max Activating Token Index: 365

Text #10

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1381113 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1089571 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1680469 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 1.5834. Min Range: -1.5834

Max Act: 0.9288. Min Act: -0.0000

Data Index: 418467 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1675181 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 1.5834. Min Range: -1.5834

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1920441 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 1.5834. Min Range: -1.5834

Max Act: 1.0142. Min Act: -0.0000

Data Index: 758320 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 1.5834. Min Range: -1.5834

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1170278 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.5834. Min Range: -1.5834

Max Act: 0.9780. Min Act: -0.0000

Data Index: 845931 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.5834. Min Range: -1.5834

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1051235 (The Pile)

Max Activating Token Index: 297