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

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

Neuron 2951 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.9776. Min Act: -0.0000

Data Index: 976826 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.3995. Min Act: -0.0000

Data Index: 268283 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.6669. Min Act: -0.0000

Data Index: 811815 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.3949. Min Act: -0.0000

Data Index: 910838 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.2485. Min Act: -0.0000

Data Index: 152864 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.8870. Min Act: -0.0000

Data Index: 952097 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.9880. Min Act: -0.0000

Data Index: 572252 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.1539. Min Act: -0.0000

Data Index: 1158047 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.3080. Min Act: -0.0000

Data Index: 1200162 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.1232. Min Act: -0.0000

Data Index: 903168 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.8852. Min Act: -0.0000

Data Index: 325961 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.8184. Min Act: -0.0000

Data Index: 1353104 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.0424. Min Act: -0.0000

Data Index: 842010 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.5820. Min Act: -0.0000

Data Index: 337249 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 4.9776. Min Range: -4.9776

Max Act: 4.0195. Min Act: -0.0000

Data Index: 927914 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.6910. Min Act: -0.0000

Data Index: 89496 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.8133. Min Act: -0.0000

Data Index: 534082 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.7423. Min Act: -0.0000

Data Index: 974185 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.7251. Min Act: -0.0000

Data Index: 1133619 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 4.9776. Min Range: -4.9776

Max Act: 3.6938. Min Act: -0.0000

Data Index: 1009288 (C4 (Web Text))

Max Activating Token Index: 360