Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1634 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.7078. Min Act: -0.0001

Data Index: 839972 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.6302. Min Act: -0.0001

Data Index: 241721 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.6155. Min Act: -0.0001

Data Index: 1176693 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5194. Min Act: -0.0001

Data Index: 186210 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5399. Min Act: -0.0001

Data Index: 526948 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5533. Min Act: -0.0001

Data Index: 898593 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5326. Min Act: -0.0001

Data Index: 264027 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5344. Min Act: -0.0001

Data Index: 975639 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.4820. Min Act: -0.0001

Data Index: 1194412 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5402. Min Act: -0.0001

Data Index: 846818 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5120. Min Act: -0.0001

Data Index: 745602 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5105. Min Act: -0.0001

Data Index: 109301 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.4905. Min Act: -0.0001

Data Index: 1147996 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5208. Min Act: -0.0001

Data Index: 118872 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5043. Min Act: -0.0001

Data Index: 1105118 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5026. Min Act: -0.0001

Data Index: 193305 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.5000. Min Act: -0.0001

Data Index: 142397 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.4652. Min Act: -0.0001

Data Index: 952773 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.4825. Min Act: -0.0001

Data Index: 180072 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.7078. Min Range: -0.7078

Max Act: 0.4529. Min Act: -0.0001

Data Index: 1306388 (C4 (Web Text))

Max Activating Token Index: 140