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

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

Neuron 6117 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0139. Min Range: -1.0139

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1095423 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1016148 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8644. Min Act: 0.0000

Data Index: 512324 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7841. Min Act: 0.0000

Data Index: 886139 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8244. Min Act: -0.0000

Data Index: 387038 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7825. Min Act: -0.0000

Data Index: 271031 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7645. Min Act: -0.0000

Data Index: 831211 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7737. Min Act: -0.0000

Data Index: 918143 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7507. Min Act: -0.0000

Data Index: 52932 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7130. Min Act: 0.0000

Data Index: 815131 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7545. Min Act: -0.0000

Data Index: 689751 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7140. Min Act: 0.0000

Data Index: 696335 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6897. Min Act: 0.0001

Data Index: 128797 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.7226. Min Act: 0.0001

Data Index: 299121 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6611. Min Act: -0.0000

Data Index: 223611 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6536. Min Act: 0.0000

Data Index: 636120 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6714. Min Act: 0.0000

Data Index: 407591 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6443. Min Act: -0.0000

Data Index: 931874 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1160291 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.6760. Min Act: -0.0000

Data Index: 412234 (C4 (Web Text))

Max Activating Token Index: 836