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

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

Neuron 1334 in Layer 1

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: 2.4458. Min Range: -2.4458

Max Act: 2.4458. Min Act: -0.0002

Data Index: 106353 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.3354. Min Act: -0.0002

Data Index: 395327 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.2955. Min Act: -0.0002

Data Index: 377672 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.2015. Min Act: -0.0002

Data Index: 900361 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1548. Min Act: -0.0002

Data Index: 29691 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1469. Min Act: -0.0002

Data Index: 1233907 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1518. Min Act: -0.0002

Data Index: 564443 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1966. Min Act: -0.0002

Data Index: 1037106 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1834. Min Act: -0.0002

Data Index: 1152540 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1487. Min Act: -0.0002

Data Index: 594519 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1442. Min Act: -0.0002

Data Index: 357396 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1329. Min Act: -0.0002

Data Index: 1268623 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1119. Min Act: -0.0002

Data Index: 256287 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1064. Min Act: -0.0002

Data Index: 693120 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1381. Min Act: -0.0002

Data Index: 1082038 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0685. Min Act: -0.0002

Data Index: 1045522 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0530. Min Act: -0.0002

Data Index: 903037 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.1449. Min Act: -0.0002

Data Index: 1006410 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0537. Min Act: -0.0002

Data Index: 900159 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 2.4458. Min Range: -2.4458

Max Act: 2.0609. Min Act: -0.0002

Data Index: 1121373 (C4 (Web Text))

Max Activating Token Index: 598