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

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

Neuron 638 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.2227. Min Act: -0.0000

Data Index: 303112 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.2075. Min Act: -0.0000

Data Index: 652716 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.2000. Min Act: 0.0000

Data Index: 709799 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1721. Min Act: -0.0000

Data Index: 494754 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1616. Min Act: -0.0000

Data Index: 779871 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1398927 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1001922 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1515. Min Act: -0.0000

Data Index: 147388 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1562. Min Act: -0.0000

Data Index: 767603 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1569. Min Act: -0.0000

Data Index: 1468746 (Python Code)

Max Activating Token Index: 568

Text #10

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1465. Min Act: -0.0000

Data Index: 42595 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1587. Min Act: -0.0000

Data Index: 803100 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1470. Min Act: -0.0000

Data Index: 503989 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1254800 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1496537 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1410. Min Act: -0.0000

Data Index: 721547 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1389373 (Python Code)

Max Activating Token Index: 449

Text #17

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1489. Min Act: -0.0000

Data Index: 529586 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1457. Min Act: 0.0000

Data Index: 760421 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.2227. Min Range: -0.2227

Max Act: 0.1499. Min Act: -0.0000

Data Index: 176188 (C4 (Web Text))

Max Activating Token Index: 144