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

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

Neuron 3275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.7174. Min Act: -0.0001

Data Index: 891205 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6239. Min Act: -0.0000

Data Index: 350012 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.6146. Min Act: -0.0001

Data Index: 1182989 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5874. Min Act: -0.0000

Data Index: 384743 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1143836 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5603. Min Act: -0.0001

Data Index: 1258249 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5532. Min Act: -0.0001

Data Index: 864437 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5149. Min Act: -0.0001

Data Index: 215797 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4581. Min Act: -0.0000

Data Index: 586770 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5456. Min Act: -0.0001

Data Index: 87997 (C4 (Web Text))

Max Activating Token Index: 726

Text #10

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1111845 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4607. Min Act: -0.0001

Data Index: 385737 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4806. Min Act: -0.0001

Data Index: 239889 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4769. Min Act: -0.0001

Data Index: 1254009 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4518. Min Act: -0.0000

Data Index: 818178 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4885. Min Act: -0.0001

Data Index: 1201727 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4992. Min Act: -0.0001

Data Index: 144461 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4573. Min Act: -0.0000

Data Index: 905756 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4497. Min Act: -0.0001

Data Index: 25822 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.7174. Min Range: -0.7174

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1073372 (C4 (Web Text))

Max Activating Token Index: 441