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

Dataset: The Pile

Neuron 2077 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.8075. Min Act: -0.0000

Data Index: 443143 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7848. Min Act: -0.0000

Data Index: 285020 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7860. Min Act: -0.0000

Data Index: 751745 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1367467 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7709. Min Act: -0.0000

Data Index: 392836 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1299764 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.8101. Min Act: -0.0000

Data Index: 575199 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1018823 (The Pile)

Max Activating Token Index: 836

Text #8

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7182. Min Act: -0.0000

Data Index: 613085 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1126483 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1553170 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.7339. Min Act: -0.0000

Data Index: 858615 (The Pile)

Max Activating Token Index: 523

Text #12

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6886. Min Act: -0.0000

Data Index: 1610715 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6378. Min Act: -0.0000

Data Index: 686415 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1880676 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1439213 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6646. Min Act: -0.0000

Data Index: 656957 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6648. Min Act: 0.0000

Data Index: 1068172 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6382. Min Act: -0.0000

Data Index: 690391 (The Pile)

Max Activating Token Index: 410

Text #19

Max Range: 0.8101. Min Range: -0.8101

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1921098 (The Pile)

Max Activating Token Index: 253