Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1294284 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4022. Min Act: -0.0000

Data Index: 127574 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.4582. Min Act: -0.0000

Data Index: 895578 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1251201 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3344. Min Act: -0.0000

Data Index: 949163 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1034488 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1308728 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2701. Min Act: -0.0000

Data Index: 90666 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3401. Min Act: -0.0000

Data Index: 856574 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3064. Min Act: -0.0000

Data Index: 384761 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3346. Min Act: -0.0000

Data Index: 959313 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.3001. Min Act: -0.0000

Data Index: 412414 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1204087 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1234680 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1212430 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2839. Min Act: -0.0000

Data Index: 638395 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2682. Min Act: -0.0000

Data Index: 821984 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2655. Min Act: -0.0000

Data Index: 128489 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2759. Min Act: -0.0000

Data Index: 21841 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.4582. Min Range: -0.4582

Max Act: 0.2914. Min Act: -0.0000

Data Index: 790866 (C4 (Web Text))

Max Activating Token Index: 877