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

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

Neuron 2431 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: 5.9552. Min Range: -5.9552

Max Act: 5.9552. Min Act: -0.0001

Data Index: 388739 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.6845. Min Act: -0.0001

Data Index: 265126 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.5335. Min Act: -0.0001

Data Index: 1052584 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.6191. Min Act: -0.0001

Data Index: 603047 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.4150. Min Act: -0.0001

Data Index: 697390 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.1982. Min Act: -0.0001

Data Index: 837706 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.4008. Min Act: -0.0001

Data Index: 1044501 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.5056. Min Act: -0.0001

Data Index: 874270 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.4808. Min Act: -0.0001

Data Index: 1016074 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.6464. Min Act: -0.0001

Data Index: 55246 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.4577. Min Act: -0.0001

Data Index: 1017181 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.4793. Min Act: -0.0001

Data Index: 243831 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.6106. Min Act: -0.0001

Data Index: 984572 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.7530. Min Act: -0.0001

Data Index: 417447 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.1135. Min Act: -0.0001

Data Index: 860539 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.1513. Min Act: -0.0001

Data Index: 1034360 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.1465. Min Act: -0.0001

Data Index: 24068 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.4772. Min Act: -0.0001

Data Index: 1257048 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.4783. Min Act: -0.0001

Data Index: 164217 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 5.9552. Min Range: -5.9552

Max Act: 5.1361. Min Act: -0.0001

Data Index: 84449 (C4 (Web Text))

Max Activating Token Index: 673