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

Dataset: The Pile

Neuron 4742 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1614 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1203817 (The Pile)

Max Activating Token Index: 344

Text #2

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1525679 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.5620. Min Act: -0.0000

Data Index: 255089 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.5246. Min Act: -0.0000

Data Index: 477381 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1980608 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.4280. Min Act: -0.0000

Data Index: 873366 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.4623. Min Act: -0.0000

Data Index: 1471688 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.4154. Min Act: -0.0000

Data Index: 1899151 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1654885 (The Pile)

Max Activating Token Index: 338

Text #10

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.4475. Min Act: -0.0000

Data Index: 906744 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.3549. Min Act: -0.0000

Data Index: 301663 (The Pile)

Max Activating Token Index: 315

Text #12

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.3442. Min Act: -0.0000

Data Index: 759903 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.3237. Min Act: -0.0000

Data Index: 1427499 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1886034 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1118909 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1741928 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1456422 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1088160 (The Pile)

Max Activating Token Index: 494

Text #19

Max Range: 1.7053. Min Range: -1.7053

Max Act: 1.3265. Min Act: -0.0000

Data Index: 683215 (The Pile)

Max Activating Token Index: 207