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

Dataset: The Pile

Neuron 1219 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: 3.7392. Min Range: -3.7392

Max Act: 3.7392. Min Act: -0.0000

Data Index: 763262 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2303. Min Act: -0.0000

Data Index: 388242 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3138. Min Act: -0.0000

Data Index: 851283 (The Pile)

Max Activating Token Index: 764

Text #3

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.4503. Min Act: -0.0000

Data Index: 1712818 (The Pile)

Max Activating Token Index: 599

Text #4

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.2299. Min Act: -0.0000

Data Index: 1587269 (The Pile)

Max Activating Token Index: 1021

Text #5

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.3556. Min Act: -0.0000

Data Index: 232279 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.0480. Min Act: -0.0000

Data Index: 609610 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.8282. Min Act: -0.0000

Data Index: 1052068 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.9578. Min Act: -0.0000

Data Index: 986878 (The Pile)

Max Activating Token Index: 821

Text #9

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.9235. Min Act: -0.0000

Data Index: 166816 (The Pile)

Max Activating Token Index: 28

Text #10

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.7021. Min Act: -0.0000

Data Index: 1765403 (The Pile)

Max Activating Token Index: 543

Text #11

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.8117. Min Act: -0.0000

Data Index: 1682359 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.4964. Min Act: -0.0000

Data Index: 812369 (The Pile)

Max Activating Token Index: 795

Text #13

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.6226. Min Act: -0.0000

Data Index: 406941 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.6132. Min Act: -0.0000

Data Index: 1835472 (The Pile)

Max Activating Token Index: 698

Text #15

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.5963. Min Act: -0.0000

Data Index: 1668274 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.5845. Min Act: -0.0000

Data Index: 1019395 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.7070. Min Act: -0.0000

Data Index: 1953356 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.7183. Min Act: -0.0000

Data Index: 1953437 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 3.7392. Min Range: -3.7392

Max Act: 2.4496. Min Act: -0.0000

Data Index: 1812568 (The Pile)

Max Activating Token Index: 853