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

Dataset: The Pile

Neuron 248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6320. Min Range: -7.6320

Max Act: 7.3914. Min Act: -0.0000

Data Index: 1544137 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 7.6320. Min Range: -7.6320

Max Act: 7.3071. Min Act: -0.0000

Data Index: 520613 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 7.6320. Min Range: -7.6320

Max Act: 7.4982. Min Act: -0.0000

Data Index: 544771 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 7.6320. Min Range: -7.6320

Max Act: 7.6320. Min Act: -0.0000

Data Index: 1204141 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 7.6320. Min Range: -7.6320

Max Act: 7.2315. Min Act: -0.0000

Data Index: 1880117 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.7397. Min Act: -0.0000

Data Index: 1399602 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.6647. Min Act: -0.0000

Data Index: 271361 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.9686. Min Act: -0.0000

Data Index: 1286853 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.8918. Min Act: -0.0000

Data Index: 704152 (The Pile)

Max Activating Token Index: 71

Text #9

Max Range: 7.6320. Min Range: -7.6320

Max Act: 7.0043. Min Act: -0.0000

Data Index: 289111 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.6231. Min Act: -0.0000

Data Index: 1629655 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.8434. Min Act: -0.0000

Data Index: 1847687 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.9402. Min Act: -0.0000

Data Index: 1057840 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.7116. Min Act: -0.0000

Data Index: 1855890 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.9992. Min Act: -0.0000

Data Index: 1770439 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.4513. Min Act: -0.0000

Data Index: 1860478 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.9258. Min Act: -0.0000

Data Index: 310199 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.5243. Min Act: -0.0000

Data Index: 270927 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.3469. Min Act: -0.0000

Data Index: 78781 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 7.6320. Min Range: -7.6320

Max Act: 6.3178. Min Act: -0.0000

Data Index: 1126200 (The Pile)

Max Activating Token Index: 312