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

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

Neuron 3471 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.2148. Min Act: -0.0001

Data Index: 901072 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.2105. Min Act: -0.0000

Data Index: 291784 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1540. Min Act: -0.0001

Data Index: 58780 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1753. Min Act: -0.0001

Data Index: 100807 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1494. Min Act: -0.0001

Data Index: 638467 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1163338 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1097209 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1614. Min Act: -0.0001

Data Index: 676161 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1579. Min Act: -0.0001

Data Index: 449409 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1053688 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1585. Min Act: -0.0001

Data Index: 385135 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1476. Min Act: -0.0001

Data Index: 910099 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1331184 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1450. Min Act: -0.0001

Data Index: 716920 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1002648 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1073701 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1499. Min Act: -0.0001

Data Index: 1508321 (Python Code)

Max Activating Token Index: 891

Text #17

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1393. Min Act: -0.0000

Data Index: 963624 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1250870 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.2148. Min Range: -0.2148

Max Act: 0.1376. Min Act: -0.0001

Data Index: 166307 (C4 (Web Text))

Max Activating Token Index: 373