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

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

Neuron 4910 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: 0.5280. Min Range: -0.5280

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1379816 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1578347 (Python Code)

Max Activating Token Index: 949

Text #2

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1591610 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1615581 (Python Code)

Max Activating Token Index: 438

Text #4

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1528561 (Python Code)

Max Activating Token Index: 310

Text #5

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1440774 (Python Code)

Max Activating Token Index: 941

Text #6

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1619849 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3605. Min Act: -0.0000

Data Index: 1559483 (Python Code)

Max Activating Token Index: 331

Text #8

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1439198 (Python Code)

Max Activating Token Index: 206

Text #9

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1464845 (Python Code)

Max Activating Token Index: 201

Text #10

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1551023 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3524. Min Act: -0.0000

Data Index: 1600690 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1473236 (Python Code)

Max Activating Token Index: 291

Text #13

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1580416 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1594153 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1632661 (Python Code)

Max Activating Token Index: 615

Text #16

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1612674 (Python Code)

Max Activating Token Index: 512

Text #17

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1476534 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1613683 (Python Code)

Max Activating Token Index: 792

Text #19

Max Range: 0.5280. Min Range: -0.5280

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1582443 (Python Code)

Max Activating Token Index: 225