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

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

Neuron 784 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6910. Min Act: -0.0000

Data Index: 1183880 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.8268. Min Act: -0.0000

Data Index: 418144 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.2988. Min Act: -0.0000

Data Index: 1276231 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.4048. Min Act: -0.0000

Data Index: 557924 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.7264. Min Act: -0.0000

Data Index: 229600 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.5230. Min Act: -0.0000

Data Index: 1285998 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6440. Min Act: -0.0000

Data Index: 298958 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.6321. Min Act: -0.0000

Data Index: 560861 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.4392. Min Act: -0.0000

Data Index: 742284 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.3551. Min Act: -0.0000

Data Index: 431234 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.1868. Min Act: -0.0000

Data Index: 1275739 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.1288. Min Act: -0.0000

Data Index: 722551 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0716. Min Act: -0.0000

Data Index: 986663 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.1759. Min Act: -0.0000

Data Index: 507348 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0127. Min Act: -0.0000

Data Index: 1023396 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.0053. Min Act: -0.0000

Data Index: 523031 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.9812. Min Act: -0.0000

Data Index: 459257 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 3.8268. Min Range: -3.8268

Max Act: 3.3124. Min Act: -0.0000

Data Index: 354879 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.8917. Min Act: -0.0000

Data Index: 1345914 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 3.8268. Min Range: -3.8268

Max Act: 2.6780. Min Act: -0.0000

Data Index: 281715 (C4 (Web Text))

Max Activating Token Index: 253