Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1130 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0575. Min Act: -0.0003

Data Index: 772820 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0541. Min Act: -0.0003

Data Index: 592881 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1258976 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0525. Min Act: -0.0003

Data Index: 778504 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0525. Min Act: -0.0003

Data Index: 1136817 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0511. Min Act: -0.0004

Data Index: 516193 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1308321 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0499. Min Act: -0.0003

Data Index: 525049 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0493. Min Act: -0.0003

Data Index: 380052 (C4 (Web Text))

Max Activating Token Index: 537

Text #9

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0500. Min Act: -0.0003

Data Index: 1235104 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0483. Min Act: -0.0003

Data Index: 438094 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0489. Min Act: -0.0003

Data Index: 203005 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1221783 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1616945 (Python Code)

Max Activating Token Index: 708

Text #14

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0485. Min Act: -0.0003

Data Index: 883831 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0494. Min Act: -0.0003

Data Index: 432049 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0485. Min Act: -0.0004

Data Index: 141770 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0489. Min Act: -0.0003

Data Index: 153744 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0486. Min Act: -0.0003

Data Index: 746258 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0478. Min Act: -0.0003

Data Index: 28613 (C4 (Web Text))

Max Activating Token Index: 333