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

Dataset: The Pile

Neuron 67 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.1537. Min Act: -0.0000

Data Index: 1135710 (The Pile)

Max Activating Token Index: 312

Text #1

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.2505. Min Act: -0.0000

Data Index: 153163 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.6610. Min Act: -0.0000

Data Index: 1179577 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.8989. Min Act: -0.0000

Data Index: 1151322 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.6499. Min Act: -0.0000

Data Index: 488275 (The Pile)

Max Activating Token Index: 318

Text #5

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.4152. Min Act: -0.0000

Data Index: 1035090 (The Pile)

Max Activating Token Index: 351

Text #6

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.2848. Min Act: -0.0000

Data Index: 880641 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.4254. Min Act: -0.0000

Data Index: 1767910 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.1760. Min Act: -0.0000

Data Index: 275404 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.4600. Min Act: -0.0000

Data Index: 1677405 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.8020. Min Act: -0.0000

Data Index: 471288 (The Pile)

Max Activating Token Index: 645

Text #11

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1446258 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1997127 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1378479 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.6377. Min Act: -0.0000

Data Index: 1076000 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1797028 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.3756. Min Act: -0.0000

Data Index: 798548 (The Pile)

Max Activating Token Index: 217

Text #17

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1086577 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.2456. Min Act: -0.0000

Data Index: 262796 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 3.2505. Min Range: -3.2505

Max Act: 1.3156. Min Act: -0.0000

Data Index: 244302 (The Pile)

Max Activating Token Index: 358