Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 753 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0004

Data Index: 1076261 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0366. Min Act: -0.0004

Data Index: 641262 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0355. Min Act: -0.0004

Data Index: 1148370 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1229844 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0354. Min Act: -0.0004

Data Index: 79350 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1186395 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0346. Min Act: -0.0004

Data Index: 112213 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0343. Min Act: -0.0004

Data Index: 337691 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0342. Min Act: -0.0004

Data Index: 774425 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0347. Min Act: -0.0004

Data Index: 910328 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0346. Min Act: -0.0004

Data Index: 640545 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0339. Min Act: -0.0004

Data Index: 727723 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0343. Min Act: -0.0004

Data Index: 393537 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0334. Min Act: -0.0005

Data Index: 154864 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1133008 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1094674 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0330. Min Act: -0.0004

Data Index: 710887 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1124748 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0329. Min Act: -0.0004

Data Index: 916785 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0329. Min Act: -0.0004

Data Index: 1201659 (C4 (Web Text))

Max Activating Token Index: 879