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

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

Neuron 495 in Layer 1

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: 2.1097. Min Range: -2.1097

Max Act: 2.1097. Min Act: -0.0003

Data Index: 579053 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 2.1097. Min Range: -2.1097

Max Act: 2.0010. Min Act: -0.0002

Data Index: 1025429 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.9468. Min Act: -0.0002

Data Index: 316396 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.8796. Min Act: -0.0002

Data Index: 755897 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.8509. Min Act: -0.0002

Data Index: 928893 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.9056. Min Act: -0.0002

Data Index: 1018250 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.8406. Min Act: -0.0002

Data Index: 895205 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.8521. Min Act: -0.0002

Data Index: 1135011 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.8135. Min Act: -0.0002

Data Index: 977403 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7633. Min Act: -0.0002

Data Index: 535212 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7279. Min Act: -0.0002

Data Index: 143218 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7557. Min Act: -0.0002

Data Index: 630626 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7246. Min Act: -0.0002

Data Index: 449920 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7251. Min Act: -0.0002

Data Index: 1058928 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7095. Min Act: -0.0002

Data Index: 468 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7271. Min Act: -0.0002

Data Index: 540770 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7404. Min Act: -0.0002

Data Index: 487744 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7288. Min Act: -0.0002

Data Index: 469075 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7082. Min Act: -0.0003

Data Index: 1285014 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 2.1097. Min Range: -2.1097

Max Act: 1.7027. Min Act: -0.0002

Data Index: 1332667 (C4 (Web Text))

Max Activating Token Index: 572