Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1464 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0438. Min Range: -1.0438

Max Act: 1.0438. Min Act: -0.0001

Data Index: 1366633 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.6975. Min Act: -0.0001

Data Index: 1386671 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1520859 (Python Code)

Max Activating Token Index: 593

Text #3

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.6201. Min Act: -0.0001

Data Index: 1458403 (Python Code)

Max Activating Token Index: 270

Text #4

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5645. Min Act: -0.0001

Data Index: 1411861 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5687. Min Act: -0.0001

Data Index: 1529834 (Python Code)

Max Activating Token Index: 771

Text #6

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5452. Min Act: -0.0001

Data Index: 510873 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5296. Min Act: -0.0001

Data Index: 654953 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5435. Min Act: -0.0001

Data Index: 1623644 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1392758 (Python Code)

Max Activating Token Index: 478

Text #10

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1385033 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5562. Min Act: -0.0001

Data Index: 984837 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5290. Min Act: -0.0001

Data Index: 538895 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5880. Min Act: -0.0001

Data Index: 1635431 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1412405 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.4864. Min Act: -0.0001

Data Index: 1031134 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5073. Min Act: -0.0001

Data Index: 1397241 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5194. Min Act: -0.0001

Data Index: 1542392 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5514. Min Act: -0.0001

Data Index: 1457023 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 1.0438. Min Range: -1.0438

Max Act: 0.5128. Min Act: -0.0001

Data Index: 1484631 (Python Code)

Max Activating Token Index: 1005