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

Dataset: The Pile

Neuron 232 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1946019 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2595. Min Act: -0.0000

Data Index: 329134 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1087597 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2264. Min Act: -0.0000

Data Index: 935415 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2220. Min Act: -0.0000

Data Index: 11341 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1121331 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2206. Min Act: -0.0000

Data Index: 73517 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1972814 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1975. Min Act: -0.0000

Data Index: 1357104 (The Pile)

Max Activating Token Index: 683

Text #9

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1790537 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1708. Min Act: -0.0000

Data Index: 541351 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1611303 (The Pile)

Max Activating Token Index: 360

Text #12

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1611499 (The Pile)

Max Activating Token Index: 836

Text #13

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1997364 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1025082 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1709010 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1874. Min Act: -0.0000

Data Index: 231737 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1884. Min Act: -0.0000

Data Index: 445842 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1685788 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 0.2595. Min Range: -0.2595

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1649478 (The Pile)

Max Activating Token Index: 688