Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.8580. Min Act: -0.0001

Data Index: 1427246 (Python Code)

Max Activating Token Index: 535

Text #1

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7690. Min Act: -0.0001

Data Index: 1449763 (Python Code)

Max Activating Token Index: 1014

Text #2

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.7198. Min Act: -0.0001

Data Index: 1559832 (Python Code)

Max Activating Token Index: 924

Text #3

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6797. Min Act: -0.0001

Data Index: 1391639 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6468. Min Act: -0.0001

Data Index: 1464392 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6667. Min Act: -0.0000

Data Index: 988086 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6333. Min Act: -0.0001

Data Index: 1561963 (Python Code)

Max Activating Token Index: 560

Text #7

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6528. Min Act: -0.0001

Data Index: 1374590 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6304. Min Act: -0.0001

Data Index: 1533538 (Python Code)

Max Activating Token Index: 613

Text #9

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1360392 (Python Code)

Max Activating Token Index: 743

Text #10

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1363673 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.5703. Min Act: -0.0001

Data Index: 1395136 (Python Code)

Max Activating Token Index: 535

Text #12

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4423. Min Act: -0.0001

Data Index: 1583263 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4548. Min Act: -0.0001

Data Index: 1615340 (Python Code)

Max Activating Token Index: 548

Text #14

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4834. Min Act: -0.0001

Data Index: 1456821 (Python Code)

Max Activating Token Index: 393

Text #15

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4432. Min Act: -0.0001

Data Index: 1460404 (Python Code)

Max Activating Token Index: 965

Text #16

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1418823 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4082. Min Act: -0.0001

Data Index: 1406156 (Python Code)

Max Activating Token Index: 655

Text #18

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4559. Min Act: -0.0001

Data Index: 1546449 (Python Code)

Max Activating Token Index: 787

Text #19

Max Range: 0.8580. Min Range: -0.8580

Max Act: 0.4525. Min Act: -0.0001

Data Index: 1592337 (Python Code)

Max Activating Token Index: 432