Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5032 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0519. Min Act: -0.0002

Data Index: 995121 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0514. Min Act: -0.0002

Data Index: 63443 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1050790 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0495. Min Act: -0.0002

Data Index: 347201 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1255635 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0420. Min Act: -0.0002

Data Index: 846391 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1242219 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0516. Min Act: -0.0002

Data Index: 172418 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0487. Min Act: -0.0002

Data Index: 547561 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1410502 (Python Code)

Max Activating Token Index: 223

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1549491 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0439. Min Act: -0.0002

Data Index: 681580 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0418. Min Act: -0.0002

Data Index: 42061 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0442. Min Act: -0.0002

Data Index: 644057 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0452. Min Act: -0.0002

Data Index: 123083 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0495. Min Act: -0.0002

Data Index: 770751 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0464. Min Act: -0.0002

Data Index: 614254 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1183557 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0438. Min Act: -0.0002

Data Index: 879775 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1181581 (C4 (Web Text))

Max Activating Token Index: 461