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

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

Neuron 2628 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: 0.2076. Min Range: -0.2076

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1025511 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1957. Min Act: -0.0001

Data Index: 356394 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1886. Min Act: -0.0001

Data Index: 252323 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1866. Min Act: -0.0001

Data Index: 928450 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1829. Min Act: -0.0001

Data Index: 471095 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1830. Min Act: -0.0001

Data Index: 855348 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1860. Min Act: -0.0001

Data Index: 805603 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1849. Min Act: -0.0001

Data Index: 133892 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1202693 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1811. Min Act: -0.0001

Data Index: 858813 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1811. Min Act: -0.0001

Data Index: 509360 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1803. Min Act: -0.0001

Data Index: 401792 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1738. Min Act: -0.0001

Data Index: 466613 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1736. Min Act: -0.0001

Data Index: 204249 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1726. Min Act: -0.0001

Data Index: 411096 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1717. Min Act: -0.0001

Data Index: 995679 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1788. Min Act: -0.0001

Data Index: 223705 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1771. Min Act: -0.0001

Data Index: 455276 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1762. Min Act: -0.0001

Data Index: 762239 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.2076. Min Range: -0.2076

Max Act: 0.1753. Min Act: -0.0001

Data Index: 474831 (C4 (Web Text))

Max Activating Token Index: 142