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

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

Neuron 1441 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6725. Min Range: -3.6725

Max Act: 3.5831. Min Act: -0.0000

Data Index: 23876 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 3.6725. Min Range: -3.6725

Max Act: 3.6725. Min Act: -0.0000

Data Index: 72962 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 3.6725. Min Range: -3.6725

Max Act: 3.2248. Min Act: -0.0000

Data Index: 278266 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 3.6725. Min Range: -3.6725

Max Act: 3.1163. Min Act: -0.0000

Data Index: 1127922 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.7787. Min Act: -0.0000

Data Index: 213099 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.4930. Min Act: -0.0000

Data Index: 144541 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.5442. Min Act: -0.0000

Data Index: 813697 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.4980. Min Act: -0.0000

Data Index: 71119 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.1211. Min Act: -0.0000

Data Index: 506130 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.0920. Min Act: -0.0000

Data Index: 760866 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.6725. Min Range: -3.6725

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1226049 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.1968. Min Act: -0.0000

Data Index: 98513 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.0173. Min Act: -0.0000

Data Index: 1355216 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 3.6725. Min Range: -3.6725

Max Act: 1.9981. Min Act: -0.0000

Data Index: 230117 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 3.6725. Min Range: -3.6725

Max Act: 1.8908. Min Act: -0.0000

Data Index: 447560 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.0142. Min Act: -0.0000

Data Index: 716844 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.1097. Min Act: -0.0000

Data Index: 1193342 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 3.6725. Min Range: -3.6725

Max Act: 2.0589. Min Act: -0.0000

Data Index: 319961 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 3.6725. Min Range: -3.6725

Max Act: 1.9549. Min Act: -0.0000

Data Index: 427798 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.6725. Min Range: -3.6725

Max Act: 1.8131. Min Act: -0.0000

Data Index: 321585 (C4 (Web Text))

Max Activating Token Index: 284