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

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

Neuron 532 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: -0.0004

Data Index: 682390 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0509. Min Act: -0.0005

Data Index: 886243 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0502. Min Act: -0.0005

Data Index: 1057021 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0499. Min Act: -0.0005

Data Index: 1332232 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0475. Min Act: -0.0005

Data Index: 131080 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0481. Min Act: -0.0005

Data Index: 283399 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0484. Min Act: -0.0005

Data Index: 1230764 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0485. Min Act: -0.0005

Data Index: 431433 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0473. Min Act: -0.0005

Data Index: 45692 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0471. Min Act: -0.0005

Data Index: 694103 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0476. Min Act: -0.0005

Data Index: 453886 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0467. Min Act: -0.0004

Data Index: 819210 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0455. Min Act: -0.0005

Data Index: 221650 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0454. Min Act: -0.0004

Data Index: 968105 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0444. Min Act: -0.0005

Data Index: 326954 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0459. Min Act: -0.0004

Data Index: 314358 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0434. Min Act: -0.0005

Data Index: 1138430 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0451. Min Act: -0.0005

Data Index: 227062 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0459. Min Act: -0.0005

Data Index: 1166766 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0475. Min Act: -0.0005

Data Index: 442862 (C4 (Web Text))

Max Activating Token Index: 380