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

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

Neuron 4952 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.7225. Min Act: -0.0000

Data Index: 1452465 (Python Code)

Max Activating Token Index: 825

Text #1

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.8864. Min Act: -0.0000

Data Index: 1449468 (Python Code)

Max Activating Token Index: 847

Text #2

Max Range: 2.1186. Min Range: -2.1186

Max Act: 2.1186. Min Act: -0.0000

Data Index: 1635025 (Python Code)

Max Activating Token Index: 841

Text #3

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.9441. Min Act: -0.0000

Data Index: 1639560 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.9057. Min Act: -0.0000

Data Index: 1591212 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 2.1186. Min Range: -2.1186

Max Act: 2.0021. Min Act: -0.0000

Data Index: 1283143 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 2.1186. Min Range: -2.1186

Max Act: 2.0125. Min Act: -0.0000

Data Index: 1393003 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.7700. Min Act: -0.0000

Data Index: 1439241 (Python Code)

Max Activating Token Index: 776

Text #8

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.8460. Min Act: -0.0000

Data Index: 1562592 (Python Code)

Max Activating Token Index: 1002

Text #9

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.9978. Min Act: -0.0000

Data Index: 1154731 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.8104. Min Act: -0.0000

Data Index: 271530 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.8766. Min Act: -0.0000

Data Index: 1298861 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.8058. Min Act: -0.0000

Data Index: 1361456 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1473602 (Python Code)

Max Activating Token Index: 679

Text #14

Max Range: 2.1186. Min Range: -2.1186

Max Act: 2.0165. Min Act: -0.0000

Data Index: 1421234 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.9450. Min Act: -0.0000

Data Index: 929801 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.7751. Min Act: -0.0000

Data Index: 1369685 (Python Code)

Max Activating Token Index: 868

Text #17

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.7694. Min Act: -0.0000

Data Index: 1384274 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.8145. Min Act: -0.0000

Data Index: 1638197 (Python Code)

Max Activating Token Index: 644

Text #19

Max Range: 2.1186. Min Range: -2.1186

Max Act: 1.7759. Min Act: -0.0000

Data Index: 1446513 (Python Code)

Max Activating Token Index: 860