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

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

Neuron 1968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2169. Min Range: -4.2169

Max Act: 4.2169. Min Act: -0.0000

Data Index: 1334814 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.9513. Min Act: -0.0000

Data Index: 109171 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.8693. Min Act: -0.0000

Data Index: 713729 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.8506. Min Act: -0.0000

Data Index: 460081 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.3697. Min Act: -0.0000

Data Index: 1025758 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.2740. Min Act: -0.0000

Data Index: 824697 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.2807. Min Act: -0.0000

Data Index: 408740 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.1154. Min Act: -0.0000

Data Index: 430673 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.8441. Min Act: -0.0000

Data Index: 868528 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.1551. Min Act: -0.0000

Data Index: 157025 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 4.2169. Min Range: -4.2169

Max Act: 3.1609. Min Act: -0.0000

Data Index: 934027 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.7521. Min Act: -0.0000

Data Index: 622907 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.7887. Min Act: -0.0000

Data Index: 839232 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.7828. Min Act: -0.0000

Data Index: 67606 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.6537. Min Act: -0.0000

Data Index: 525965 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.7585. Min Act: -0.0000

Data Index: 968644 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.5916. Min Act: -0.0000

Data Index: 206634 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.7265. Min Act: -0.0000

Data Index: 1334866 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.6914. Min Act: -0.0000

Data Index: 380064 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 4.2169. Min Range: -4.2169

Max Act: 2.5091. Min Act: -0.0000

Data Index: 687760 (C4 (Web Text))

Max Activating Token Index: 106