Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1976 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.4654. Min Act: -0.0001

Data Index: 362377 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3313. Min Act: -0.0001

Data Index: 1126117 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3800. Min Act: -0.0001

Data Index: 454777 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.3058. Min Act: -0.0001

Data Index: 340345 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2931. Min Act: -0.0001

Data Index: 278211 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2405. Min Act: -0.0001

Data Index: 1353003 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2295. Min Act: -0.0001

Data Index: 571162 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2383. Min Act: -0.0001

Data Index: 745059 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2576. Min Act: -0.0001

Data Index: 47501 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1669. Min Act: -0.0001

Data Index: 649408 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.2293. Min Act: -0.0001

Data Index: 847248 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.0639. Min Act: -0.0001

Data Index: 374082 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1907. Min Act: -0.0001

Data Index: 563763 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1328. Min Act: -0.0001

Data Index: 586939 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1383. Min Act: -0.0001

Data Index: 876954 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1252. Min Act: -0.0001

Data Index: 704743 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1488. Min Act: -0.0001

Data Index: 458694 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.0432. Min Act: -0.0001

Data Index: 199378 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.1321. Min Act: -0.0001

Data Index: 429315 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.4654. Min Range: -1.4654

Max Act: 1.0830. Min Act: -0.0001

Data Index: 724895 (C4 (Web Text))

Max Activating Token Index: 633