Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2829 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1697. Min Act: -0.0001

Data Index: 999338 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1925. Min Act: -0.0001

Data Index: 983774 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1776. Min Act: -0.0001

Data Index: 594163 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1691. Min Act: -0.0001

Data Index: 66048 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1676. Min Act: -0.0001

Data Index: 317348 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1483. Min Act: -0.0001

Data Index: 291233 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1584. Min Act: -0.0001

Data Index: 652365 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1574. Min Act: -0.0001

Data Index: 446203 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1176225 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1179913 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1602. Min Act: -0.0001

Data Index: 327850 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1013211 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1460. Min Act: -0.0001

Data Index: 716830 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1443. Min Act: -0.0001

Data Index: 189030 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1522. Min Act: -0.0001

Data Index: 793001 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1394. Min Act: -0.0001

Data Index: 868475 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1399. Min Act: -0.0001

Data Index: 281410 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1058804 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1216471 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.1925. Min Range: -0.1925

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1341612 (C4 (Web Text))

Max Activating Token Index: 496