Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 448 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6016. Min Range: -1.6016

Max Act: 1.6016. Min Act: -0.0000

Data Index: 520560 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.9132. Min Act: -0.0000

Data Index: 402065 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8618. Min Act: -0.0000

Data Index: 380295 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7932. Min Act: -0.0000

Data Index: 101148 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8067. Min Act: -0.0001

Data Index: 1252035 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.8098. Min Act: -0.0000

Data Index: 967714 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7101. Min Act: -0.0000

Data Index: 89597 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7360. Min Act: -0.0000

Data Index: 670132 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7463. Min Act: -0.0001

Data Index: 262998 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7245. Min Act: -0.0000

Data Index: 239932 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1262676 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.6890. Min Act: -0.0000

Data Index: 800856 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7431. Min Act: -0.0000

Data Index: 871685 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7547. Min Act: -0.0000

Data Index: 564168 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7169. Min Act: -0.0001

Data Index: 857775 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1161360 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7066. Min Act: -0.0000

Data Index: 795924 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1021350 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.6502. Min Act: -0.0000

Data Index: 632403 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 1.6016. Min Range: -1.6016

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1197884 (C4 (Web Text))

Max Activating Token Index: 260