Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2872 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.5109. Min Act: -0.0003

Data Index: 538431 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4988. Min Act: -0.0003

Data Index: 618523 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.5108. Min Act: -0.0003

Data Index: 797008 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4457. Min Act: -0.0003

Data Index: 545442 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4464. Min Act: -0.0003

Data Index: 791920 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4191. Min Act: -0.0003

Data Index: 567655 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4353. Min Act: -0.0003

Data Index: 1330043 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4660. Min Act: -0.0003

Data Index: 532549 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4098. Min Act: -0.0003

Data Index: 176044 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4320. Min Act: -0.0003

Data Index: 395878 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4312. Min Act: -0.0003

Data Index: 558278 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4582. Min Act: -0.0003

Data Index: 1349364 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4131. Min Act: -0.0003

Data Index: 307260 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4479. Min Act: -0.0003

Data Index: 490135 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3963. Min Act: -0.0003

Data Index: 22745 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4362. Min Act: -0.0003

Data Index: 1125881 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.3971. Min Act: -0.0003

Data Index: 210082 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4267. Min Act: -0.0003

Data Index: 670831 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4292. Min Act: -0.0003

Data Index: 489746 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.5109. Min Range: -0.5109

Max Act: 0.4015. Min Act: -0.0003

Data Index: 652453 (C4 (Web Text))

Max Activating Token Index: 137