Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1960 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0006

Data Index: 602162 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0676. Min Act: -0.0006

Data Index: 1359408 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0612. Min Act: -0.0006

Data Index: 632199 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0582. Min Act: -0.0006

Data Index: 841466 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0553. Min Act: -0.0006

Data Index: 724078 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0553. Min Act: -0.0006

Data Index: 485131 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0544. Min Act: -0.0006

Data Index: 21285 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0513. Min Act: -0.0006

Data Index: 803292 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0518. Min Act: -0.0006

Data Index: 305532 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0518. Min Act: -0.0006

Data Index: 703764 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0502. Min Act: -0.0006

Data Index: 606831 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0485. Min Act: -0.0006

Data Index: 156184 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0493. Min Act: -0.0006

Data Index: 647755 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0481. Min Act: -0.0006

Data Index: 102301 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0501. Min Act: -0.0006

Data Index: 251644 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0500. Min Act: -0.0006

Data Index: 621457 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0485. Min Act: -0.0006

Data Index: 644738 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0478. Min Act: -0.0006

Data Index: 1162391 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0474. Min Act: -0.0006

Data Index: 680163 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0493. Min Act: -0.0006

Data Index: 489146 (C4 (Web Text))

Max Activating Token Index: 95