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

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

Neuron 430 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2501. Min Range: -2.2501

Max Act: 2.2333. Min Act: -0.0000

Data Index: 1443000 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 2.2501. Min Range: -2.2501

Max Act: 2.2501. Min Act: -0.0000

Data Index: 1427756 (Python Code)

Max Activating Token Index: 396

Text #2

Max Range: 2.2501. Min Range: -2.2501

Max Act: 2.1441. Min Act: -0.0000

Data Index: 1640448 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.9793. Min Act: -0.0000

Data Index: 1564844 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 2.2501. Min Range: -2.2501

Max Act: 2.0705. Min Act: -0.0000

Data Index: 1501300 (Python Code)

Max Activating Token Index: 404

Text #5

Max Range: 2.2501. Min Range: -2.2501

Max Act: 2.0012. Min Act: -0.0000

Data Index: 390010 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.7961. Min Act: -0.0000

Data Index: 1544705 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.9813. Min Act: -0.0000

Data Index: 1598121 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.8691. Min Act: -0.0000

Data Index: 799933 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.8195. Min Act: -0.0000

Data Index: 1373024 (Python Code)

Max Activating Token Index: 250

Text #10

Max Range: 2.2501. Min Range: -2.2501

Max Act: 2.0405. Min Act: -0.0000

Data Index: 1378671 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.8082. Min Act: -0.0000

Data Index: 1438051 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.7744. Min Act: -0.0000

Data Index: 1389653 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.7568. Min Act: -0.0000

Data Index: 1140748 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.7444. Min Act: -0.0000

Data Index: 781246 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.8084. Min Act: -0.0000

Data Index: 335734 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.6201. Min Act: -0.0000

Data Index: 1335815 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.6243. Min Act: -0.0000

Data Index: 586191 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.7078. Min Act: -0.0000

Data Index: 1414776 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 2.2501. Min Range: -2.2501

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1499083 (Python Code)

Max Activating Token Index: 613