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

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

Neuron 3604 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.8012. Min Act: -0.0001

Data Index: 1043023 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.5388. Min Act: -0.0001

Data Index: 831883 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.6107. Min Act: -0.0001

Data Index: 138024 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.7460. Min Act: -0.0001

Data Index: 989099 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.5707. Min Act: -0.0001

Data Index: 439803 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.4429. Min Act: -0.0001

Data Index: 384631 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.4591. Min Act: -0.0001

Data Index: 245546 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.2720. Min Act: -0.0001

Data Index: 96841 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3658. Min Act: -0.0001

Data Index: 177912 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3150. Min Act: -0.0001

Data Index: 1219137 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.2136. Min Act: -0.0001

Data Index: 562578 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3158. Min Act: -0.0001

Data Index: 240143 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.4756. Min Act: -0.0001

Data Index: 48705 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3246. Min Act: -0.0001

Data Index: 237496 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.2410. Min Act: -0.0001

Data Index: 876201 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3186. Min Act: -0.0001

Data Index: 960162 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.2825. Min Act: -0.0001

Data Index: 256990 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.2632. Min Act: -0.0001

Data Index: 558857 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.3144. Min Act: -0.0001

Data Index: 890840 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.8012. Min Range: -1.8012

Max Act: 1.2765. Min Act: -0.0001

Data Index: 350413 (C4 (Web Text))

Max Activating Token Index: 510