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

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

Neuron 3117 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5430. Min Range: -5.5430

Max Act: 5.5430. Min Act: -0.0000

Data Index: 234388 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 5.5430. Min Range: -5.5430

Max Act: 5.1245. Min Act: -0.0001

Data Index: 1316800 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 5.5430. Min Range: -5.5430

Max Act: 5.0993. Min Act: -0.0000

Data Index: 480376 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.9950. Min Act: -0.0000

Data Index: 126749 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.6193. Min Act: -0.0000

Data Index: 921040 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.7519. Min Act: -0.0000

Data Index: 1312668 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.3185. Min Act: -0.0001

Data Index: 890538 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 5.5430. Min Range: -5.5430

Max Act: 3.6903. Min Act: -0.0000

Data Index: 1220011 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.2481. Min Act: -0.0001

Data Index: 418883 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.0381. Min Act: -0.0000

Data Index: 702324 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.0368. Min Act: -0.0001

Data Index: 1031634 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 5.5430. Min Range: -5.5430

Max Act: 3.9767. Min Act: -0.0000

Data Index: 838599 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 5.5430. Min Range: -5.5430

Max Act: 3.9369. Min Act: -0.0000

Data Index: 262921 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.0903. Min Act: -0.0000

Data Index: 805182 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.0611. Min Act: -0.0000

Data Index: 33005 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 5.5430. Min Range: -5.5430

Max Act: 3.8940. Min Act: -0.0000

Data Index: 1175124 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.0394. Min Act: -0.0001

Data Index: 679153 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 5.5430. Min Range: -5.5430

Max Act: 3.6793. Min Act: -0.0000

Data Index: 762678 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 5.5430. Min Range: -5.5430

Max Act: 3.8628. Min Act: -0.0000

Data Index: 216769 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 5.5430. Min Range: -5.5430

Max Act: 4.0354. Min Act: -0.0001

Data Index: 323500 (C4 (Web Text))

Max Activating Token Index: 185