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

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

Neuron 5200 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.9689. Min Act: -0.0001

Data Index: 910383 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.9282. Min Act: -0.0001

Data Index: 1000331 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8845. Min Act: -0.0001

Data Index: 846712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8393. Min Act: -0.0001

Data Index: 161973 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8159. Min Act: -0.0001

Data Index: 1352843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.8046. Min Act: -0.0001

Data Index: 1345143 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7724. Min Act: -0.0001

Data Index: 596647 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7796. Min Act: -0.0001

Data Index: 554236 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7656. Min Act: -0.0001

Data Index: 304571 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7673. Min Act: -0.0001

Data Index: 986964 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7663. Min Act: -0.0001

Data Index: 1347725 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7516. Min Act: -0.0001

Data Index: 1036946 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7661. Min Act: -0.0001

Data Index: 861330 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7528. Min Act: -0.0001

Data Index: 532182 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7329. Min Act: -0.0001

Data Index: 1225796 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1116961 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7120. Min Act: -0.0001

Data Index: 1047916 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7152. Min Act: -0.0001

Data Index: 1294752 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7158. Min Act: -0.0001

Data Index: 760166 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.9689. Min Range: -0.9689

Max Act: 0.7232. Min Act: -0.0001

Data Index: 159593 (C4 (Web Text))

Max Activating Token Index: 161