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

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

Neuron 6029 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1058. Min Range: -4.1058

Max Act: 4.1058. Min Act: -0.0000

Data Index: 234487 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 4.1058. Min Range: -4.1058

Max Act: 4.0584. Min Act: -0.0000

Data Index: 158745 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.8690. Min Act: -0.0000

Data Index: 305372 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.9841. Min Act: -0.0000

Data Index: 644333 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.7571. Min Act: -0.0000

Data Index: 894080 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.7127. Min Act: -0.0000

Data Index: 1131838 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.8499. Min Act: -0.0000

Data Index: 725132 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.6444. Min Act: -0.0000

Data Index: 220787 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.8094. Min Act: -0.0000

Data Index: 1198802 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.7906. Min Act: -0.0000

Data Index: 126247 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.6238. Min Act: -0.0000

Data Index: 570790 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.7845. Min Act: -0.0000

Data Index: 935506 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.9650. Min Act: -0.0000

Data Index: 983182 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.6008. Min Act: -0.0000

Data Index: 667407 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.7574. Min Act: -0.0000

Data Index: 473460 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.7031. Min Act: -0.0000

Data Index: 243235 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.7087. Min Act: -0.0000

Data Index: 1351322 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.6895. Min Act: -0.0000

Data Index: 540960 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.5220. Min Act: -0.0000

Data Index: 613538 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 4.1058. Min Range: -4.1058

Max Act: 3.6646. Min Act: 0.0000

Data Index: 1164266 (C4 (Web Text))

Max Activating Token Index: 857