Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 975 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0134. Min Act: -0.0006

Data Index: 786057 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0133. Min Act: -0.0006

Data Index: 600089 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0006

Data Index: 674660 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1254283 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0131. Min Act: -0.0006

Data Index: 1221941 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0006

Data Index: 1023504 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0130. Min Act: -0.0006

Data Index: 132887 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0006

Data Index: 614146 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1347909 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 116222 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 282645 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 647016 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1256653 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0006

Data Index: 584049 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0006

Data Index: 813192 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1531077 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0006

Data Index: 56308 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0124. Min Act: -0.0006

Data Index: 539498 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0126. Min Act: -0.0006

Data Index: 695329 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0134. Min Range: -0.0134

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1035936 (C4 (Web Text))

Max Activating Token Index: 38