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

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

Neuron 5789 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.2748. Min Act: -0.0000

Data Index: 20897 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.9497. Min Act: -0.0000

Data Index: 1288995 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.2223. Min Act: -0.0000

Data Index: 60543 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.1123. Min Act: -0.0000

Data Index: 99521 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.3598. Min Act: -0.0000

Data Index: 916301 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.8462. Min Act: -0.0000

Data Index: 224834 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.0601. Min Act: -0.0000

Data Index: 331800 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.4383. Min Act: -0.0000

Data Index: 1040465 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.3820. Min Act: -0.0000

Data Index: 1279690 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.9390. Min Act: -0.0000

Data Index: 913285 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 5.9497. Min Range: -5.9497

Max Act: 5.0739. Min Act: -0.0000

Data Index: 437998 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.7097. Min Act: -0.0000

Data Index: 382009 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.4880. Min Act: -0.0000

Data Index: 713783 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.6648. Min Act: -0.0000

Data Index: 582847 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.6156. Min Act: -0.0000

Data Index: 235780 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.4312. Min Act: -0.0000

Data Index: 156331 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.6127. Min Act: -0.0000

Data Index: 744759 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.5574. Min Act: -0.0000

Data Index: 1301542 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.7171. Min Act: -0.0000

Data Index: 576131 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 5.9497. Min Range: -5.9497

Max Act: 4.5147. Min Act: -0.0000

Data Index: 429929 (C4 (Web Text))

Max Activating Token Index: 497