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

Dataset: The Pile

Neuron 824 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: 3.4929. Min Range: -3.4929

Max Act: 3.4929. Min Act: -0.0000

Data Index: 1356852 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 3.4929. Min Range: -3.4929

Max Act: 3.1522. Min Act: -0.0000

Data Index: 711929 (The Pile)

Max Activating Token Index: 841

Text #2

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.7632. Min Act: -0.0000

Data Index: 327014 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.5267. Min Act: -0.0000

Data Index: 1870563 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.4320. Min Act: -0.0000

Data Index: 1560526 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.5129. Min Act: -0.0000

Data Index: 1512999 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.3157. Min Act: -0.0000

Data Index: 1522633 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.9183. Min Act: -0.0000

Data Index: 492907 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.2535. Min Act: -0.0000

Data Index: 1518451 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.9192. Min Act: -0.0000

Data Index: 201367 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.1121. Min Act: -0.0000

Data Index: 1951443 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 3.4929. Min Range: -3.4929

Max Act: 2.3724. Min Act: -0.0000

Data Index: 1459558 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.8061. Min Act: -0.0000

Data Index: 1877770 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.9822. Min Act: -0.0000

Data Index: 242247 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.9381. Min Act: -0.0000

Data Index: 1675901 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.9131. Min Act: -0.0000

Data Index: 798292 (The Pile)

Max Activating Token Index: 342

Text #16

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.7756. Min Act: -0.0000

Data Index: 440470 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.7280. Min Act: -0.0000

Data Index: 236273 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.7357. Min Act: -0.0000

Data Index: 895529 (The Pile)

Max Activating Token Index: 803

Text #19

Max Range: 3.4929. Min Range: -3.4929

Max Act: 1.8257. Min Act: -0.0000

Data Index: 888533 (The Pile)

Max Activating Token Index: 926