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

Dataset: The Pile

Neuron 3643 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1192. Min Act: -0.0000

Data Index: 1251621 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1948. Min Act: -0.0000

Data Index: 397253 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0954. Min Act: -0.0000

Data Index: 342459 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1228. Min Act: -0.0000

Data Index: 708057 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1754799 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9638. Min Act: 0.0000

Data Index: 959274 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1253320 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1341231 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8818. Min Act: 0.0000

Data Index: 331761 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9084. Min Act: -0.0000

Data Index: 1975898 (The Pile)

Max Activating Token Index: 77

Text #10

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1191003 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1839989 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7716. Min Act: -0.0000

Data Index: 198948 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8575. Min Act: -0.0000

Data Index: 303819 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1049244 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1356039 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7910. Min Act: -0.0000

Data Index: 380011 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7322. Min Act: -0.0000

Data Index: 142425 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1009088 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 1.1948. Min Range: -1.1948

Max Act: 0.8111. Min Act: -0.0000

Data Index: 216543 (The Pile)

Max Activating Token Index: 244