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

Dataset: The Pile

Neuron 2763 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.8391. Min Act: -0.0000

Data Index: 921568 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.5802. Min Act: -0.0000

Data Index: 506680 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.3865. Min Act: -0.0000

Data Index: 1375207 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.1752. Min Act: -0.0000

Data Index: 714499 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4403. Min Act: -0.0000

Data Index: 96425 (The Pile)

Max Activating Token Index: 529

Text #5

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.1407. Min Act: -0.0000

Data Index: 368285 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.3217. Min Act: -0.0000

Data Index: 24328 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.6048. Min Act: -0.0000

Data Index: 254584 (The Pile)

Max Activating Token Index: 797

Text #8

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.0090. Min Act: -0.0000

Data Index: 98061 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.0031. Min Act: -0.0000

Data Index: 1979308 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.9986. Min Act: -0.0000

Data Index: 482031 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.1504. Min Act: -0.0000

Data Index: 1959506 (The Pile)

Max Activating Token Index: 417

Text #12

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.7567. Min Act: -0.0000

Data Index: 731205 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.2758. Min Act: -0.0000

Data Index: 1590374 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.0819. Min Act: -0.0000

Data Index: 1005589 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.6788. Min Act: -0.0000

Data Index: 757847 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.0141. Min Act: -0.0000

Data Index: 433682 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.4869. Min Act: -0.0000

Data Index: 137186 (The Pile)

Max Activating Token Index: 432

Text #18

Max Range: 5.8391. Min Range: -5.8391

Max Act: 4.8805. Min Act: -0.0000

Data Index: 846996 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 5.8391. Min Range: -5.8391

Max Act: 5.2451. Min Act: -0.0000

Data Index: 852348 (The Pile)

Max Activating Token Index: 957