Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1462 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 2.2454. Min Range: -2.2454

Max Act: 2.2454. Min Act: -0.0002

Data Index: 1046060 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 2.2454. Min Range: -2.2454

Max Act: 2.1433. Min Act: -0.0002

Data Index: 594152 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 2.2454. Min Range: -2.2454

Max Act: 2.1625. Min Act: -0.0002

Data Index: 97262 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 2.2454. Min Range: -2.2454

Max Act: 2.0594. Min Act: -0.0002

Data Index: 299405 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 2.2454. Min Range: -2.2454

Max Act: 2.0485. Min Act: -0.0002

Data Index: 817466 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9330. Min Act: -0.0002

Data Index: 1111417 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9410. Min Act: -0.0002

Data Index: 822621 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.2454. Min Range: -2.2454

Max Act: 2.0011. Min Act: -0.0002

Data Index: 111117 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.8823. Min Act: -0.0002

Data Index: 114063 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9646. Min Act: -0.0002

Data Index: 1251573 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.8581. Min Act: -0.0002

Data Index: 943856 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.8567. Min Act: -0.0002

Data Index: 986455 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9113. Min Act: -0.0002

Data Index: 506039 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9108. Min Act: -0.0002

Data Index: 204209 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9203. Min Act: -0.0002

Data Index: 1157520 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9017. Min Act: -0.0002

Data Index: 453172 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9293. Min Act: -0.0002

Data Index: 1267073 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.9107. Min Act: -0.0002

Data Index: 1099585 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.8206. Min Act: -0.0002

Data Index: 836903 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 2.2454. Min Range: -2.2454

Max Act: 1.8889. Min Act: -0.0002

Data Index: 1283186 (C4 (Web Text))

Max Activating Token Index: 10