Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1864 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.3635. Min Act: -0.0001

Data Index: 869971 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.3527. Min Act: -0.0001

Data Index: 996419 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.3409. Min Act: -0.0001

Data Index: 855328 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.3723. Min Act: -0.0001

Data Index: 1310467 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.3694. Min Act: -0.0001

Data Index: 1291266 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.1783. Min Act: -0.0001

Data Index: 263948 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.2099. Min Act: -0.0001

Data Index: 358984 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.2814. Min Act: -0.0001

Data Index: 1068035 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0488. Min Act: -0.0001

Data Index: 342636 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.1147. Min Act: -0.0001

Data Index: 265229 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0258. Min Act: -0.0001

Data Index: 843551 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0011. Min Act: -0.0001

Data Index: 412649 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9645. Min Act: -0.0001

Data Index: 885059 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9629. Min Act: -0.0001

Data Index: 1089330 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.3723. Min Range: -1.3723

Max Act: 1.0487. Min Act: -0.0001

Data Index: 493312 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9830. Min Act: -0.0001

Data Index: 1272767 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9721. Min Act: -0.0001

Data Index: 1551734 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9456. Min Act: -0.0001

Data Index: 1066292 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9250. Min Act: -0.0001

Data Index: 871021 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.3723. Min Range: -1.3723

Max Act: 0.9145. Min Act: -0.0001

Data Index: 609625 (C4 (Web Text))

Max Activating Token Index: 626