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

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

Neuron 4471 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1358645 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.7077. Min Act: -0.0000

Data Index: 1603049 (Python Code)

Max Activating Token Index: 474

Text #2

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3917. Min Act: -0.0000

Data Index: 318744 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.4095. Min Act: -0.0000

Data Index: 911283 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3770. Min Act: -0.0000

Data Index: 1521025 (Python Code)

Max Activating Token Index: 763

Text #5

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1560189 (Python Code)

Max Activating Token Index: 613

Text #6

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1407937 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1396872 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3888. Min Act: -0.0000

Data Index: 1553449 (Python Code)

Max Activating Token Index: 200

Text #9

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.2941. Min Act: -0.0000

Data Index: 712170 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1361456 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.0851. Min Act: -0.0000

Data Index: 305762 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.1642. Min Act: -0.0000

Data Index: 1109350 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1374572 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3377. Min Act: -0.0000

Data Index: 1380123 (Python Code)

Max Activating Token Index: 561

Text #15

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1360043 (Python Code)

Max Activating Token Index: 692

Text #16

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3318. Min Act: -0.0000

Data Index: 293484 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1615444 (Python Code)

Max Activating Token Index: 922

Text #18

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.2395. Min Act: -0.0000

Data Index: 297954 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1449123 (Python Code)

Max Activating Token Index: 708