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

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

Neuron 2690 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.7164. Min Act: -0.0001

Data Index: 1087482 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.7033. Min Act: -0.0001

Data Index: 475033 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.6676. Min Act: -0.0001

Data Index: 498282 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.7069. Min Act: -0.0001

Data Index: 269824 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.5015. Min Act: -0.0001

Data Index: 368553 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.4578. Min Act: -0.0001

Data Index: 1324784 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.2393. Min Act: -0.0001

Data Index: 29873 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.4235. Min Act: -0.0001

Data Index: 763915 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.2453. Min Act: -0.0001

Data Index: 890937 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.3871. Min Act: -0.0001

Data Index: 513654 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.3378. Min Act: -0.0001

Data Index: 826885 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.2955. Min Act: -0.0001

Data Index: 104176 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.2740. Min Act: -0.0001

Data Index: 824730 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.2641. Min Act: -0.0001

Data Index: 72720 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.2201. Min Act: -0.0001

Data Index: 234655 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.3989. Min Act: -0.0001

Data Index: 839999 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.2301. Min Act: -0.0001

Data Index: 1038810 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.1629. Min Act: -0.0001

Data Index: 1118453 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.1717. Min Act: -0.0001

Data Index: 963374 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 1.7164. Min Range: -1.7164

Max Act: 1.1752. Min Act: -0.0001

Data Index: 1332640 (C4 (Web Text))

Max Activating Token Index: 256