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

Dataset: The Pile

Neuron 4362 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: 0.2684. Min Range: -0.2684

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1114876 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2684. Min Act: -0.0000

Data Index: 229896 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2502. Min Act: -0.0000

Data Index: 439925 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2158. Min Act: -0.0000

Data Index: 568107 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1101769 (The Pile)

Max Activating Token Index: 808

Text #5

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1951843 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1946. Min Act: -0.0000

Data Index: 538402 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1036383 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1507192 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2144. Min Act: -0.0000

Data Index: 633140 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1998. Min Act: -0.0000

Data Index: 736408 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2055. Min Act: -0.0000

Data Index: 397582 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2263. Min Act: -0.0000

Data Index: 265780 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2095. Min Act: -0.0000

Data Index: 810666 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2030. Min Act: -0.0000

Data Index: 163000 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1267856 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1849. Min Act: -0.0000

Data Index: 457896 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1903. Min Act: -0.0000

Data Index: 5513 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1724219 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1366452 (The Pile)

Max Activating Token Index: 117