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

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

Neuron 2397 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8129. Min Range: -2.8129

Max Act: 2.8129. Min Act: -0.0001

Data Index: 1095550 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 2.8129. Min Range: -2.8129

Max Act: 2.0209. Min Act: -0.0000

Data Index: 684672 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 2.8129. Min Range: -2.8129

Max Act: 2.0000. Min Act: -0.0000

Data Index: 507546 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 2.8129. Min Range: -2.8129

Max Act: 2.0073. Min Act: -0.0000

Data Index: 20147 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 2.8129. Min Range: -2.8129

Max Act: 2.0540. Min Act: -0.0000

Data Index: 470335 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.7515. Min Act: -0.0001

Data Index: 259904 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.7825. Min Act: -0.0001

Data Index: 1213701 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.8028. Min Act: -0.0001

Data Index: 925185 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.6285. Min Act: -0.0000

Data Index: 854205 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.7814. Min Act: -0.0000

Data Index: 651397 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.7626. Min Act: -0.0000

Data Index: 955004 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.7418. Min Act: -0.0000

Data Index: 401436 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.5627. Min Act: -0.0000

Data Index: 85977 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.7345. Min Act: -0.0001

Data Index: 998511 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.5644. Min Act: -0.0000

Data Index: 1191190 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.7308. Min Act: -0.0001

Data Index: 243635 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.5833. Min Act: -0.0001

Data Index: 329627 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.5928. Min Act: -0.0000

Data Index: 273388 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.6465. Min Act: -0.0000

Data Index: 856331 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 2.8129. Min Range: -2.8129

Max Act: 1.5812. Min Act: -0.0001

Data Index: 357398 (C4 (Web Text))

Max Activating Token Index: 773