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

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

Neuron 3386 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1377. Min Range: -3.1377

Max Act: 3.1377. Min Act: -0.0000

Data Index: 1037493 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.7802. Min Act: -0.0000

Data Index: 99115 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.7630. Min Act: -0.0000

Data Index: 882701 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.7699. Min Act: -0.0000

Data Index: 998538 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.6985. Min Act: -0.0000

Data Index: 510970 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.5455. Min Act: -0.0000

Data Index: 334143 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.8129. Min Act: -0.0000

Data Index: 1138971 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.5286. Min Act: -0.0000

Data Index: 206911 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.6559. Min Act: -0.0000

Data Index: 1207679 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.6132. Min Act: -0.0000

Data Index: 666381 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.7515. Min Act: -0.0000

Data Index: 940631 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.5578. Min Act: -0.0000

Data Index: 1335150 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.5372. Min Act: -0.0000

Data Index: 813746 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.5086. Min Act: -0.0000

Data Index: 1250646 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.6199. Min Act: -0.0000

Data Index: 442953 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.4459. Min Act: -0.0000

Data Index: 159240 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.5399. Min Act: -0.0000

Data Index: 542641 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.4038. Min Act: -0.0000

Data Index: 996266 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.3889. Min Act: -0.0000

Data Index: 38589 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 3.1377. Min Range: -3.1377

Max Act: 2.3800. Min Act: -0.0000

Data Index: 1096396 (C4 (Web Text))

Max Activating Token Index: 140