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

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

Neuron 1752 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: 3.9351. Min Range: -3.9351

Max Act: 3.6287. Min Act: -0.0000

Data Index: 78340 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.6785. Min Act: -0.0000

Data Index: 921466 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.9351. Min Act: -0.0000

Data Index: 810508 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.7058. Min Act: -0.0000

Data Index: 515942 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.5234. Min Act: -0.0000

Data Index: 812668 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.8452. Min Act: -0.0000

Data Index: 261647 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.6171. Min Act: -0.0000

Data Index: 226907 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4716. Min Act: -0.0000

Data Index: 194415 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4002. Min Act: -0.0000

Data Index: 1136979 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.7357. Min Act: -0.0000

Data Index: 119050 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.5489. Min Act: -0.0000

Data Index: 1038208 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4945. Min Act: -0.0000

Data Index: 381628 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.6636. Min Act: -0.0000

Data Index: 1313827 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4984. Min Act: -0.0000

Data Index: 983743 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4500. Min Act: -0.0000

Data Index: 885637 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4388. Min Act: -0.0000

Data Index: 1065956 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4363. Min Act: -0.0000

Data Index: 632156 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4187. Min Act: -0.0000

Data Index: 1225922 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.2531. Min Act: -0.0000

Data Index: 906245 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 3.9351. Min Range: -3.9351

Max Act: 3.4163. Min Act: -0.0000

Data Index: 403504 (C4 (Web Text))

Max Activating Token Index: 841