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

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

Neuron 1887 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: 0.6452. Min Range: -0.6452

Max Act: 0.5740. Min Act: -0.0000

Data Index: 869852 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.6452. Min Act: -0.0000

Data Index: 189493 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.4531. Min Act: -0.0000

Data Index: 407108 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1111618 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1591277 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1529017 (Python Code)

Max Activating Token Index: 107

Text #6

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1603505 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1404653 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1431690 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.2939. Min Act: -0.0000

Data Index: 1393449 (Python Code)

Max Activating Token Index: 767

Text #10

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3021. Min Act: -0.0001

Data Index: 1589492 (Python Code)

Max Activating Token Index: 672

Text #11

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1553570 (Python Code)

Max Activating Token Index: 655

Text #12

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1544676 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3144. Min Act: -0.0000

Data Index: 1573138 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3039. Min Act: -0.0000

Data Index: 1504515 (Python Code)

Max Activating Token Index: 986

Text #15

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.2918. Min Act: -0.0000

Data Index: 1468785 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1598788 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.3079. Min Act: -0.0000

Data Index: 1555634 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1626822 (Python Code)

Max Activating Token Index: 785

Text #19

Max Range: 0.6452. Min Range: -0.6452

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1614528 (Python Code)

Max Activating Token Index: 136