Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 716 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1556456 (Python Code)

Max Activating Token Index: 371

Text #1

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1498532 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1646066 (Python Code)

Max Activating Token Index: 557

Text #3

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1448534 (Python Code)

Max Activating Token Index: 309

Text #4

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1176598 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.6740. Min Act: -0.0000

Data Index: 543580 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1393584 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1464088 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1645385 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1403022 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1464841 (Python Code)

Max Activating Token Index: 725

Text #12

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1557807 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1403788 (Python Code)

Max Activating Token Index: 142

Text #14

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1402180 (Python Code)

Max Activating Token Index: 896

Text #15

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1316559 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1473947 (Python Code)

Max Activating Token Index: 753

Text #17

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1370262 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.4613. Min Act: -0.0000

Data Index: 1637862 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 0.7762. Min Range: -0.7762

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1411863 (Python Code)

Max Activating Token Index: 654