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

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

Neuron 2418 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: 4.6475. Min Range: -4.6475

Max Act: 4.5942. Min Act: -0.0000

Data Index: 1651578 (Python Code)

Max Activating Token Index: 274

Text #1

Max Range: 4.6475. Min Range: -4.6475

Max Act: 4.6443. Min Act: -0.0000

Data Index: 1464914 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 4.6475. Min Range: -4.6475

Max Act: 4.5558. Min Act: -0.0000

Data Index: 1553272 (Python Code)

Max Activating Token Index: 87

Text #3

Max Range: 4.6475. Min Range: -4.6475

Max Act: 4.5453. Min Act: -0.0000

Data Index: 1465049 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 4.6475. Min Range: -4.6475

Max Act: 4.6475. Min Act: -0.0000

Data Index: 1498516 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 4.6475. Min Range: -4.6475

Max Act: 4.5860. Min Act: -0.0000

Data Index: 1377319 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 4.6475. Min Range: -4.6475

Max Act: 3.9738. Min Act: -0.0000

Data Index: 1484532 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 4.6475. Min Range: -4.6475

Max Act: 3.7986. Min Act: -0.0000

Data Index: 602517 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 4.6475. Min Range: -4.6475

Max Act: 3.7883. Min Act: -0.0000

Data Index: 1451750 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 4.6475. Min Range: -4.6475

Max Act: 3.2229. Min Act: -0.0000

Data Index: 851430 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 4.6475. Min Range: -4.6475

Max Act: 3.1476. Min Act: -0.0000

Data Index: 293397 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.6483. Min Act: -0.0000

Data Index: 952151 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.8015. Min Act: -0.0000

Data Index: 853244 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 4.6475. Min Range: -4.6475

Max Act: 3.1081. Min Act: -0.0000

Data Index: 127308 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.6810. Min Act: -0.0000

Data Index: 1408145 (Python Code)

Max Activating Token Index: 255

Text #15

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.4310. Min Act: -0.0000

Data Index: 1272562 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.6440. Min Act: -0.0000

Data Index: 1424251 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.9964. Min Act: -0.0000

Data Index: 844206 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.7572. Min Act: -0.0000

Data Index: 652580 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 4.6475. Min Range: -4.6475

Max Act: 2.7251. Min Act: -0.0000

Data Index: 1581386 (Python Code)

Max Activating Token Index: 458