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

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

Neuron 4488 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: 3.3738. Min Range: -3.3738

Max Act: 3.3096. Min Act: -0.0000

Data Index: 124054 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.2816. Min Act: -0.0000

Data Index: 830800 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.3738. Min Act: -0.0000

Data Index: 1263063 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.0091. Min Act: -0.0000

Data Index: 1101552 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.2862. Min Act: -0.0000

Data Index: 1114089 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.1178. Min Act: -0.0000

Data Index: 776143 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.0988. Min Act: -0.0000

Data Index: 424180 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.9112. Min Act: -0.0000

Data Index: 1203589 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.0469. Min Act: -0.0000

Data Index: 1243201 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.8984. Min Act: -0.0000

Data Index: 870838 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.3738. Min Range: -3.3738

Max Act: 3.0039. Min Act: -0.0000

Data Index: 95136 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.9736. Min Act: -0.0000

Data Index: 918757 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.9568. Min Act: -0.0000

Data Index: 1027877 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.8125. Min Act: -0.0000

Data Index: 249928 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.8982. Min Act: -0.0000

Data Index: 600567 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.8789. Min Act: -0.0000

Data Index: 185153 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.8678. Min Act: -0.0000

Data Index: 1331034 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.7128. Min Act: -0.0000

Data Index: 390509 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.7060. Min Act: -0.0000

Data Index: 221497 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 3.3738. Min Range: -3.3738

Max Act: 2.6940. Min Act: -0.0000

Data Index: 738132 (C4 (Web Text))

Max Activating Token Index: 600