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

Dataset: The Pile

Neuron 4087 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: 4.9410. Min Range: -4.9410

Max Act: 4.9410. Min Act: -0.0000

Data Index: 793460 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.2466. Min Act: -0.0000

Data Index: 1099162 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.2700. Min Act: -0.0000

Data Index: 984341 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.2477. Min Act: -0.0000

Data Index: 1493418 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.8743. Min Act: -0.0000

Data Index: 1321746 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.4365. Min Act: -0.0000

Data Index: 1177484 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.6526. Min Act: -0.0000

Data Index: 239001 (The Pile)

Max Activating Token Index: 522

Text #7

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.2552. Min Act: -0.0000

Data Index: 1034483 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.7132. Min Act: -0.0000

Data Index: 1419221 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.0401. Min Act: -0.0000

Data Index: 94972 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.0129. Min Act: -0.0000

Data Index: 903224 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.1366. Min Act: -0.0000

Data Index: 1286080 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.3230. Min Act: -0.0000

Data Index: 1725709 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.9179. Min Act: -0.0000

Data Index: 541075 (The Pile)

Max Activating Token Index: 473

Text #14

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.0673. Min Act: -0.0000

Data Index: 1177602 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.8844. Min Act: -0.0000

Data Index: 1763184 (The Pile)

Max Activating Token Index: 607

Text #16

Max Range: 4.9410. Min Range: -4.9410

Max Act: 4.0192. Min Act: -0.0000

Data Index: 1271311 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.9919. Min Act: -0.0000

Data Index: 1901075 (The Pile)

Max Activating Token Index: 476

Text #18

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.8460. Min Act: -0.0000

Data Index: 1560770 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 4.9410. Min Range: -4.9410

Max Act: 3.8083. Min Act: -0.0000

Data Index: 633499 (The Pile)

Max Activating Token Index: 83