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

Dataset: The Pile

Neuron 3952 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: 0.5297. Min Range: -0.5297

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1419153 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1116430 (The Pile)

Max Activating Token Index: 141

Text #2

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.5084. Min Act: -0.0000

Data Index: 144132 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.5070. Min Act: -0.0000

Data Index: 194555 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1129007 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4948. Min Act: -0.0000

Data Index: 455661 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.5070. Min Act: -0.0000

Data Index: 159467 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1916940 (The Pile)

Max Activating Token Index: 840

Text #8

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4572. Min Act: -0.0000

Data Index: 281884 (The Pile)

Max Activating Token Index: 204

Text #9

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4565. Min Act: -0.0000

Data Index: 351614 (The Pile)

Max Activating Token Index: 874

Text #10

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4534. Min Act: -0.0000

Data Index: 149461 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1587070 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1806845 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1235368 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1776668 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1761198 (The Pile)

Max Activating Token Index: 45

Text #16

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4491. Min Act: -0.0000

Data Index: 651154 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1857116 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4180. Min Act: -0.0000

Data Index: 794622 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 0.5297. Min Range: -0.5297

Max Act: 0.4306. Min Act: -0.0000

Data Index: 969786 (The Pile)

Max Activating Token Index: 281