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

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

Neuron 462 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: 2.4385. Min Range: -2.4385

Max Act: 2.4385. Min Act: -0.0000

Data Index: 576474 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.8457. Min Act: -0.0000

Data Index: 818826 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.7144. Min Act: -0.0000

Data Index: 972540 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1066407 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.2414. Min Act: -0.0000

Data Index: 316917 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.1974. Min Act: 0.0000

Data Index: 41249 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.0308. Min Act: -0.0000

Data Index: 1512962 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1654255 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.0397. Min Act: 0.0000

Data Index: 1491146 (Python Code)

Max Activating Token Index: 676

Text #9

Max Range: 2.4385. Min Range: -2.4385

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1474313 (Python Code)

Max Activating Token Index: 478

Text #10

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1498569 (Python Code)

Max Activating Token Index: 162

Text #11

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1424236 (Python Code)

Max Activating Token Index: 458

Text #12

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1385499 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1118162 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1650948 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1574426 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.8865. Min Act: -0.0000

Data Index: 912778 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1165287 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1604300 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 2.4385. Min Range: -2.4385

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1537402 (Python Code)

Max Activating Token Index: 34