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

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

Neuron 5307 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.7838. Min Act: -0.0000

Data Index: 1370870 (Python Code)

Max Activating Token Index: 296

Text #1

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.6896. Min Act: -0.0000

Data Index: 1377112 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.7007. Min Act: -0.0000

Data Index: 1398965 (Python Code)

Max Activating Token Index: 138

Text #3

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.8254. Min Act: -0.0000

Data Index: 1404497 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 3.2505. Min Range: -3.2505

Max Act: 3.2505. Min Act: -0.0000

Data Index: 1622346 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.7080. Min Act: -0.0000

Data Index: 1459711 (Python Code)

Max Activating Token Index: 177

Text #6

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.5654. Min Act: -0.0000

Data Index: 868135 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.6494. Min Act: -0.0000

Data Index: 815845 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.4279. Min Act: -0.0000

Data Index: 1373974 (Python Code)

Max Activating Token Index: 389

Text #9

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.3931. Min Act: -0.0000

Data Index: 1478199 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.4895. Min Act: -0.0000

Data Index: 817427 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.4266. Min Act: -0.0000

Data Index: 502305 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.3025. Min Act: -0.0000

Data Index: 1272612 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.4072. Min Act: -0.0000

Data Index: 1408645 (Python Code)

Max Activating Token Index: 965

Text #14

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.2664. Min Act: -0.0000

Data Index: 364490 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.3795. Min Act: -0.0000

Data Index: 979389 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.3787. Min Act: -0.0000

Data Index: 267625 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.2503. Min Act: -0.0000

Data Index: 969010 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.2388. Min Act: -0.0000

Data Index: 1243789 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 3.2505. Min Range: -3.2505

Max Act: 2.3450. Min Act: -0.0000

Data Index: 115818 (C4 (Web Text))

Max Activating Token Index: 501