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

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

Neuron 3675 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: 4.3882. Min Range: -4.3882

Max Act: 4.3569. Min Act: -0.0000

Data Index: 665912 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1800. Min Act: -0.0000

Data Index: 129767 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.3882. Min Act: -0.0000

Data Index: 63562 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2062. Min Act: -0.0000

Data Index: 1188211 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.3678. Min Act: -0.0001

Data Index: 815665 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1839. Min Act: -0.0000

Data Index: 679348 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1953. Min Act: -0.0000

Data Index: 1333059 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.3258. Min Act: -0.0000

Data Index: 544046 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0494. Min Act: -0.0000

Data Index: 252423 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1987. Min Act: -0.0000

Data Index: 500342 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2227. Min Act: -0.0000

Data Index: 1167235 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.3708. Min Act: -0.0000

Data Index: 530087 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1883. Min Act: -0.0000

Data Index: 50849 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.3509. Min Act: -0.0000

Data Index: 581850 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0101. Min Act: -0.0000

Data Index: 910722 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1724. Min Act: -0.0000

Data Index: 841302 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1830. Min Act: -0.0000

Data Index: 1178950 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.2084. Min Act: -0.0000

Data Index: 14153 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.0457. Min Act: -0.0000

Data Index: 1078676 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 4.3882. Min Range: -4.3882

Max Act: 4.1619. Min Act: -0.0000

Data Index: 807325 (C4 (Web Text))

Max Activating Token Index: 179