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

Dataset: The Pile

Neuron 717 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: 0.9205. Min Range: -0.9205

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1317483 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1328776 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1375186 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1257985 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6410. Min Act: -0.0000

Data Index: 228375 (The Pile)

Max Activating Token Index: 1011

Text #5

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1398463 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1803720 (The Pile)

Max Activating Token Index: 622

Text #7

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5699. Min Act: -0.0000

Data Index: 538265 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5477. Min Act: -0.0000

Data Index: 890390 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5321. Min Act: -0.0000

Data Index: 963178 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5242. Min Act: -0.0000

Data Index: 347378 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.4899. Min Act: -0.0000

Data Index: 55089 (The Pile)

Max Activating Token Index: 463

Text #12

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1120467 (The Pile)

Max Activating Token Index: 256

Text #13

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1994136 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.5458. Min Act: -0.0000

Data Index: 67793 (The Pile)

Max Activating Token Index: 183

Text #15

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.4922. Min Act: -0.0000

Data Index: 102049 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1961722 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.4667. Min Act: -0.0000

Data Index: 670386 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1017774 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.9205. Min Range: -0.9205

Max Act: 0.4868. Min Act: -0.0000

Data Index: 489870 (The Pile)

Max Activating Token Index: 327