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

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

Neuron 4138 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1098073 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1990. Min Act: -0.0001

Data Index: 211608 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1291621 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1697. Min Act: -0.0001

Data Index: 819819 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1576. Min Act: -0.0001

Data Index: 396421 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1448. Min Act: -0.0001

Data Index: 523529 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1535. Min Act: -0.0001

Data Index: 749731 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1446. Min Act: -0.0001

Data Index: 548939 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1405. Min Act: -0.0001

Data Index: 872439 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1317. Min Act: -0.0001

Data Index: 954539 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1284908 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1332034 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1507. Min Act: -0.0001

Data Index: 590449 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1537. Min Act: -0.0001

Data Index: 836668 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1456. Min Act: -0.0001

Data Index: 554822 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1274. Min Act: -0.0001

Data Index: 242204 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1321. Min Act: -0.0001

Data Index: 178740 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1027130 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1277. Min Act: -0.0001

Data Index: 654366 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1230300 (C4 (Web Text))

Max Activating Token Index: 845