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

Dataset: The Pile

Neuron 2042 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: 0.3210. Min Range: -0.3210

Max Act: 0.3210. Min Act: -0.0000

Data Index: 366070 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2533. Min Act: -0.0000

Data Index: 239971 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2745. Min Act: -0.0000

Data Index: 173043 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1105345 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2500. Min Act: -0.0000

Data Index: 770887 (The Pile)

Max Activating Token Index: 98

Text #5

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2468. Min Act: -0.0000

Data Index: 768102 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2454. Min Act: -0.0000

Data Index: 383182 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.1884. Min Act: -0.0000

Data Index: 243311 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2251. Min Act: -0.0000

Data Index: 386338 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1147427 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2050. Min Act: -0.0001

Data Index: 447174 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1816810 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1550581 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2067. Min Act: -0.0000

Data Index: 375483 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1801736 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1371191 (The Pile)

Max Activating Token Index: 123

Text #16

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.1811. Min Act: -0.0000

Data Index: 917363 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.1940. Min Act: -0.0000

Data Index: 945109 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2089. Min Act: -0.0000

Data Index: 638850 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 0.3210. Min Range: -0.3210

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1177523 (The Pile)

Max Activating Token Index: 58