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

Dataset: The Pile

Neuron 1504 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1751500 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1833915 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3808. Min Act: -0.0000

Data Index: 918545 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1471931 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3152. Min Act: -0.0000

Data Index: 561332 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3458. Min Act: -0.0000

Data Index: 631241 (The Pile)

Max Activating Token Index: 87

Text #6

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1088837 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1590949 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3227. Min Act: -0.0000

Data Index: 475270 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3300. Min Act: -0.0000

Data Index: 179440 (The Pile)

Max Activating Token Index: 105

Text #10

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2856. Min Act: -0.0000

Data Index: 940032 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3148. Min Act: -0.0000

Data Index: 223717 (The Pile)

Max Activating Token Index: 461

Text #12

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1744542 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3004. Min Act: -0.0000

Data Index: 904554 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3131. Min Act: -0.0000

Data Index: 332257 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.3110. Min Act: -0.0000

Data Index: 73110 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2970. Min Act: -0.0000

Data Index: 655941 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2613. Min Act: -0.0000

Data Index: 179902 (The Pile)

Max Activating Token Index: 669

Text #18

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2867. Min Act: -0.0000

Data Index: 282461 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.4574. Min Range: -0.4574

Max Act: 0.2831. Min Act: -0.0000

Data Index: 562464 (The Pile)

Max Activating Token Index: 976