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

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

Neuron 4226 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3855. Min Range: -3.3855

Max Act: 3.3855. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.8802. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.6034. Min Act: -0.0000

Data Index: 432515 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.5232. Min Act: -0.0000

Data Index: 24892 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.6348. Min Act: -0.0000

Data Index: 159256 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.3909. Min Act: -0.0000

Data Index: 579825 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.6488. Min Act: -0.0000

Data Index: 92591 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.4961. Min Act: -0.0000

Data Index: 1095232 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.4838. Min Act: -0.0000

Data Index: 710518 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.4597. Min Act: -0.0000

Data Index: 180838 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.3011. Min Act: -0.0000

Data Index: 843395 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.4337. Min Act: -0.0000

Data Index: 464203 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.5491. Min Act: -0.0000

Data Index: 1343385 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.3662. Min Act: -0.0000

Data Index: 138744 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.3065. Min Act: -0.0000

Data Index: 506975 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.2062. Min Act: 0.0000

Data Index: 246557 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.2671. Min Act: -0.0000

Data Index: 790147 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.1340. Min Act: -0.0000

Data Index: 740369 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.3670. Min Act: -0.0000

Data Index: 314224 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 3.3855. Min Range: -3.3855

Max Act: 2.0262. Min Act: -0.0000

Data Index: 607805 (C4 (Web Text))

Max Activating Token Index: 709