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

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

Neuron 4699 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1250. Min Range: -3.1250

Max Act: 3.1250. Min Act: -0.0000

Data Index: 873723 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 3.1250. Min Range: -3.1250

Max Act: 2.6928. Min Act: -0.0000

Data Index: 472426 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.1250. Min Range: -3.1250

Max Act: 2.1609. Min Act: -0.0000

Data Index: 490728 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.8861. Min Act: -0.0000

Data Index: 467058 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.8538. Min Act: -0.0000

Data Index: 534173 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.7412. Min Act: -0.0000

Data Index: 1025781 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.7294. Min Act: -0.0000

Data Index: 1258822 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.6770. Min Act: -0.0000

Data Index: 1086164 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.5739. Min Act: -0.0000

Data Index: 148005 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.2929. Min Act: -0.0000

Data Index: 526167 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.6081. Min Act: -0.0000

Data Index: 179981 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.2970. Min Act: -0.0000

Data Index: 383072 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.3927. Min Act: -0.0000

Data Index: 491749 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.3193. Min Act: -0.0000

Data Index: 992629 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.3096. Min Act: -0.0000

Data Index: 146713 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1278542 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.2968. Min Act: -0.0000

Data Index: 843812 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.2735. Min Act: -0.0000

Data Index: 462050 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.2661. Min Act: -0.0000

Data Index: 271428 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 3.1250. Min Range: -3.1250

Max Act: 1.2310. Min Act: -0.0000

Data Index: 870296 (C4 (Web Text))

Max Activating Token Index: 670