Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 494 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 14.9314. Min Range: -14.9314

Max Act: 14.9314. Min Act: -0.0000

Data Index: 156374 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 14.9314. Min Range: -14.9314

Max Act: 12.5025. Min Act: -0.0000

Data Index: 611661 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 14.9314. Min Range: -14.9314

Max Act: 13.0666. Min Act: -0.0000

Data Index: 344415 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 14.9314. Min Range: -14.9314

Max Act: 12.7317. Min Act: -0.0000

Data Index: 160735 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 14.9314. Min Range: -14.9314

Max Act: 12.7893. Min Act: -0.0000

Data Index: 719022 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 14.9314. Min Range: -14.9314

Max Act: 12.3085. Min Act: -0.0000

Data Index: 242344 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 14.9314. Min Range: -14.9314

Max Act: 12.6917. Min Act: -0.0000

Data Index: 1102157 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 14.9314. Min Range: -14.9314

Max Act: 10.8415. Min Act: -0.0000

Data Index: 827923 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.6630. Min Act: -0.0000

Data Index: 508016 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.6030. Min Act: -0.0000

Data Index: 62276 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.3388. Min Act: 0.0001

Data Index: 1269594 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.5941. Min Act: -0.0000

Data Index: 917244 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.1529. Min Act: -0.0000

Data Index: 700255 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 14.9314. Min Range: -14.9314

Max Act: 9.1510. Min Act: -0.0000

Data Index: 477087 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.6002. Min Act: -0.0000

Data Index: 1349180 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 14.9314. Min Range: -14.9314

Max Act: 10.8418. Min Act: -0.0000

Data Index: 745352 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.2138. Min Act: -0.0000

Data Index: 401024 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.2149. Min Act: -0.0000

Data Index: 1288116 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 14.9314. Min Range: -14.9314

Max Act: 11.2472. Min Act: -0.0000

Data Index: 1118777 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 14.9314. Min Range: -14.9314

Max Act: 10.5630. Min Act: -0.0000

Data Index: 908807 (C4 (Web Text))

Max Activating Token Index: 333