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

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

Neuron 2355 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.6590. Min Act: -0.0001

Data Index: 895627 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.6719. Min Act: -0.0001

Data Index: 348100 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.6464. Min Act: -0.0001

Data Index: 13534 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.6444. Min Act: -0.0001

Data Index: 707832 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.6196. Min Act: -0.0001

Data Index: 694893 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.6057. Min Act: -0.0001

Data Index: 89197 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.6196. Min Act: -0.0001

Data Index: 1164591 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5856. Min Act: -0.0001

Data Index: 468514 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5917. Min Act: -0.0001

Data Index: 1100943 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5677. Min Act: -0.0001

Data Index: 1120031 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5921. Min Act: -0.0001

Data Index: 666588 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5521. Min Act: -0.0001

Data Index: 688302 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5260. Min Act: -0.0001

Data Index: 462645 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5558. Min Act: -0.0001

Data Index: 331483 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5748. Min Act: -0.0001

Data Index: 1219087 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5640. Min Act: -0.0001

Data Index: 541219 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5404. Min Act: -0.0001

Data Index: 695888 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5105. Min Act: -0.0001

Data Index: 1289380 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5341. Min Act: -0.0001

Data Index: 918555 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.6719. Min Range: -1.6719

Max Act: 1.5505. Min Act: -0.0001

Data Index: 67513 (C4 (Web Text))

Max Activating Token Index: 3