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

Dataset: The Pile

Neuron 2906 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: 1.4129. Min Range: -1.4129

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1561969 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1783082 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1338327 (The Pile)

Max Activating Token Index: 142

Text #3

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.2233. Min Act: -0.0000

Data Index: 626269 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1865310 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0084. Min Act: -0.0000

Data Index: 291418 (The Pile)

Max Activating Token Index: 528

Text #6

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1873751 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1625522 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1024065 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9552. Min Act: -0.0000

Data Index: 639158 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1591. Min Act: -0.0000

Data Index: 1221773 (The Pile)

Max Activating Token Index: 240

Text #11

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9968. Min Act: -0.0000

Data Index: 308448 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 1.4129. Min Range: -1.4129

Max Act: 1.1322. Min Act: -0.0000

Data Index: 558837 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.8714. Min Act: -0.0000

Data Index: 1665224 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9826. Min Act: -0.0000

Data Index: 726266 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1375083 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1479083 (The Pile)

Max Activating Token Index: 9

Text #17

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9191. Min Act: -0.0000

Data Index: 339477 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9837. Min Act: -0.0000

Data Index: 54470 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 1.4129. Min Range: -1.4129

Max Act: 0.9356. Min Act: -0.0000

Data Index: 914325 (The Pile)

Max Activating Token Index: 26