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

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

Neuron 3519 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1933. Min Act: -0.0001

Data Index: 926957 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1222787 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1580. Min Act: -0.0001

Data Index: 870360 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1618. Min Act: -0.0001

Data Index: 260305 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1607. Min Act: -0.0001

Data Index: 95591 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1505. Min Act: -0.0001

Data Index: 892673 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1558. Min Act: -0.0001

Data Index: 240124 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1488. Min Act: -0.0001

Data Index: 97208 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1069407 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1523. Min Act: -0.0001

Data Index: 721072 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1036888 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1333. Min Act: -0.0001

Data Index: 370609 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1244. Min Act: -0.0001

Data Index: 967576 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1354. Min Act: -0.0001

Data Index: 181057 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1389. Min Act: -0.0001

Data Index: 77253 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1265. Min Act: -0.0001

Data Index: 608622 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1322. Min Act: -0.0001

Data Index: 648513 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1102755 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1215. Min Act: -0.0001

Data Index: 582363 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1201063 (C4 (Web Text))

Max Activating Token Index: 420