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

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

Neuron 3204 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.2084. Min Act: -0.0001

Data Index: 219421 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1866. Min Act: -0.0000

Data Index: 456808 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1927. Min Act: -0.0000

Data Index: 418325 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1799. Min Act: -0.0000

Data Index: 122542 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1632. Min Act: -0.0000

Data Index: 89541 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1710. Min Act: -0.0000

Data Index: 21163 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1012930 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1668. Min Act: -0.0001

Data Index: 329355 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1651. Min Act: -0.0001

Data Index: 924537 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1592. Min Act: -0.0000

Data Index: 249991 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1029425 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1542. Min Act: -0.0000

Data Index: 298661 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1600. Min Act: -0.0000

Data Index: 426701 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1537. Min Act: -0.0001

Data Index: 163221 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1071650 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1508. Min Act: -0.0000

Data Index: 543567 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1507. Min Act: -0.0000

Data Index: 18723 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1493. Min Act: -0.0001

Data Index: 235140 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1385. Min Act: -0.0001

Data Index: 393533 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1336. Min Act: -0.0000

Data Index: 547678 (C4 (Web Text))

Max Activating Token Index: 204