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

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

Neuron 1650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0005

Data Index: 1253354 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0506. Min Act: -0.0005

Data Index: 883474 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0500. Min Act: -0.0005

Data Index: 572029 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0525. Min Act: -0.0005

Data Index: 425695 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0504. Min Act: -0.0005

Data Index: 547752 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0498. Min Act: -0.0005

Data Index: 1303487 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0496. Min Act: -0.0005

Data Index: 828176 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0490. Min Act: -0.0005

Data Index: 55486 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0481. Min Act: -0.0005

Data Index: 42150 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0481. Min Act: -0.0005

Data Index: 198559 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0474. Min Act: -0.0005

Data Index: 483012 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0475. Min Act: -0.0005

Data Index: 553748 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0493. Min Act: -0.0005

Data Index: 480546 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0479. Min Act: -0.0005

Data Index: 746485 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0461. Min Act: -0.0005

Data Index: 91375 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0460. Min Act: -0.0005

Data Index: 1084864 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0449. Min Act: -0.0005

Data Index: 366980 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0456. Min Act: -0.0005

Data Index: 722243 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0456. Min Act: -0.0005

Data Index: 1285995 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0455. Min Act: -0.0005

Data Index: 42113 (C4 (Web Text))

Max Activating Token Index: 813