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

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

Neuron 4392 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.7101. Min Act: -0.0000

Data Index: 851319 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.7119. Min Act: -0.0000

Data Index: 708297 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1321979 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.6250. Min Act: -0.0000

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1623987 (Python Code)

Max Activating Token Index: 963

Text #5

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4569. Min Act: -0.0000

Data Index: 154977 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1277801 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1297481 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4275. Min Act: -0.0000

Data Index: 434551 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1197876 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4043. Min Act: -0.0000

Data Index: 148864 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4230. Min Act: -0.0000

Data Index: 369084 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1548249 (Python Code)

Max Activating Token Index: 750

Text #13

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3854. Min Act: -0.0000

Data Index: 73177 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1104264 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3675. Min Act: -0.0000

Data Index: 910902 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1302312 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3913. Min Act: -0.0000

Data Index: 336717 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1644743 (Python Code)

Max Activating Token Index: 408

Text #19

Max Range: 0.7119. Min Range: -0.7119

Max Act: 0.3765. Min Act: -0.0000

Data Index: 89233 (C4 (Web Text))

Max Activating Token Index: 320