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

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

Neuron 871 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: 1.5036. Min Range: -1.5036

Max Act: 1.5036. Min Act: -0.0001

Data Index: 340133 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.3274. Min Act: -0.0001

Data Index: 25417 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1245388 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0293. Min Act: -0.0001

Data Index: 1107503 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.2035. Min Act: -0.0001

Data Index: 866612 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0267. Min Act: -0.0001

Data Index: 638022 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.2441. Min Act: -0.0001

Data Index: 515249 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.1728. Min Act: -0.0001

Data Index: 585010 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.2111. Min Act: -0.0000

Data Index: 586177 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.1488. Min Act: -0.0000

Data Index: 784825 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0433. Min Act: -0.0001

Data Index: 359651 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.5036. Min Range: -1.5036

Max Act: 0.9076. Min Act: -0.0001

Data Index: 501132 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0729. Min Act: -0.0001

Data Index: 270210 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0883. Min Act: -0.0001

Data Index: 18620 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 1.5036. Min Range: -1.5036

Max Act: 0.9898. Min Act: -0.0000

Data Index: 856381 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0168. Min Act: -0.0001

Data Index: 199001 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.5036. Min Range: -1.5036

Max Act: 0.8823. Min Act: -0.0001

Data Index: 1165008 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0709. Min Act: -0.0001

Data Index: 638654 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 1.5036. Min Range: -1.5036

Max Act: 1.0322. Min Act: -0.0001

Data Index: 1079298 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.5036. Min Range: -1.5036

Max Act: 0.9176. Min Act: -0.0001

Data Index: 39900 (C4 (Web Text))

Max Activating Token Index: 486