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

Dataset: The Pile

Neuron 2066 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: 0.7267. Min Range: -0.7267

Max Act: 0.7267. Min Act: -0.0000

Data Index: 927842 (The Pile)

Max Activating Token Index: 214

Text #1

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1880671 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6961. Min Act: -0.0000

Data Index: 763955 (The Pile)

Max Activating Token Index: 687

Text #3

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5793. Min Act: -0.0000

Data Index: 692101 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1530593 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.6027. Min Act: -0.0000

Data Index: 161350 (The Pile)

Max Activating Token Index: 703

Text #6

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5502. Min Act: -0.0000

Data Index: 318767 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5288. Min Act: -0.0000

Data Index: 275045 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1928628 (The Pile)

Max Activating Token Index: 821

Text #9

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1559416 (The Pile)

Max Activating Token Index: 369

Text #10

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1000153 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5331. Min Act: -0.0000

Data Index: 407793 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1761615 (The Pile)

Max Activating Token Index: 215

Text #13

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5302. Min Act: -0.0000

Data Index: 689089 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5524. Min Act: -0.0000

Data Index: 153450 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5009. Min Act: -0.0000

Data Index: 959053 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5388. Min Act: -0.0000

Data Index: 991398 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1781383 (The Pile)

Max Activating Token Index: 335

Text #18

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1768877 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.7267. Min Range: -0.7267

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1868874 (The Pile)

Max Activating Token Index: 727