Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.0194. Min Range: -4.0194

Max Act: 4.0194. Min Act: -0.0001

Data Index: 566180 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8385. Min Act: -0.0001

Data Index: 1109665 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8297. Min Act: -0.0000

Data Index: 658316 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.8561. Min Act: -0.0001

Data Index: 1023927 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.6680. Min Act: -0.0000

Data Index: 697853 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.4855. Min Act: -0.0001

Data Index: 523255 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.5999. Min Act: -0.0001

Data Index: 561007 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.4185. Min Act: -0.0001

Data Index: 123130 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.5710. Min Act: -0.0000

Data Index: 266290 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.5653. Min Act: -0.0001

Data Index: 1156428 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.5163. Min Act: -0.0000

Data Index: 308947 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.4423. Min Act: -0.0000

Data Index: 801862 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.2858. Min Act: -0.0000

Data Index: 575923 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.4152. Min Act: -0.0000

Data Index: 17745 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.2599. Min Act: -0.0000

Data Index: 731895 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.2488. Min Act: -0.0001

Data Index: 410604 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.3861. Min Act: -0.0000

Data Index: 606893 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.3621. Min Act: -0.0001

Data Index: 975528 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.5141. Min Act: -0.0000

Data Index: 1086212 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 4.0194. Min Range: -4.0194

Max Act: 3.3420. Min Act: -0.0000

Data Index: 362690 (C4 (Web Text))

Max Activating Token Index: 855