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

Dataset: The Pile

Neuron 3016 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: 1.9632. Min Range: -1.9632

Max Act: 1.9632. Min Act: -0.0000

Data Index: 525223 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.8981. Min Act: -0.0000

Data Index: 194531 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.7108. Min Act: -0.0000

Data Index: 679412 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1430870 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.6126. Min Act: -0.0000

Data Index: 1546864 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.5684. Min Act: -0.0000

Data Index: 285548 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.6830. Min Act: -0.0000

Data Index: 1212522 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.6032. Min Act: -0.0000

Data Index: 1881269 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.6573. Min Act: -0.0000

Data Index: 1500870 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.6271. Min Act: -0.0000

Data Index: 242323 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.4268. Min Act: -0.0000

Data Index: 826021 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.5054. Min Act: -0.0000

Data Index: 850488 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.6871. Min Act: -0.0000

Data Index: 950371 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.6875. Min Act: -0.0000

Data Index: 151908 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1056232 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.5607. Min Act: -0.0000

Data Index: 331150 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.5779. Min Act: -0.0000

Data Index: 730450 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.5317. Min Act: -0.0000

Data Index: 1586135 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.4537. Min Act: -0.0000

Data Index: 767979 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 1.9632. Min Range: -1.9632

Max Act: 1.4830. Min Act: -0.0000

Data Index: 180243 (The Pile)

Max Activating Token Index: 67