Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4718 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0419. Min Range: -1.0419

Max Act: 1.0419. Min Act: -0.0000

Data Index: 640589 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 1.0419. Min Range: -1.0419

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1192662 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 1.0419. Min Range: -1.0419

Max Act: 1.0241. Min Act: -0.0000

Data Index: 8688 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.9954. Min Act: -0.0000

Data Index: 761839 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.9559. Min Act: -0.0000

Data Index: 839864 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.9391. Min Act: -0.0000

Data Index: 724232 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.9139. Min Act: -0.0000

Data Index: 505295 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8449. Min Act: -0.0000

Data Index: 971914 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8930. Min Act: -0.0000

Data Index: 282154 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8860. Min Act: -0.0000

Data Index: 200412 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8239. Min Act: -0.0000

Data Index: 593816 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8747. Min Act: -0.0000

Data Index: 268020 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1109792 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1128817 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8314. Min Act: -0.0000

Data Index: 91131 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.7985. Min Act: -0.0000

Data Index: 609853 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8644. Min Act: -0.0000

Data Index: 318749 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.7951. Min Act: -0.0000

Data Index: 798553 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1315458 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.0419. Min Range: -1.0419

Max Act: 0.8399. Min Act: -0.0000

Data Index: 440184 (C4 (Web Text))

Max Activating Token Index: 56