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

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

Neuron 949 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1268115 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5683. Min Act: -0.0000

Data Index: 539054 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1039100 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5580. Min Act: -0.0000

Data Index: 996213 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1163844 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5090. Min Act: -0.0000

Data Index: 220689 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4641. Min Act: -0.0000

Data Index: 838630 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1136146 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4442. Min Act: -0.0000

Data Index: 843110 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4594. Min Act: -0.0000

Data Index: 670142 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4449. Min Act: -0.0000

Data Index: 817258 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1019226 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.5004. Min Act: -0.0000

Data Index: 162104 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4819. Min Act: -0.0000

Data Index: 295408 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4671. Min Act: -0.0000

Data Index: 300177 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1135851 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4597. Min Act: -0.0000

Data Index: 426412 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4456. Min Act: -0.0000

Data Index: 131301 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4483. Min Act: -0.0000

Data Index: 433927 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4380. Min Act: -0.0000

Data Index: 854102 (C4 (Web Text))

Max Activating Token Index: 434