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

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

Neuron 4139 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: 0.5052. Min Range: -0.5052

Max Act: 0.5052. Min Act: -0.0001

Data Index: 230000 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4811. Min Act: -0.0001

Data Index: 43699 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4526. Min Act: -0.0001

Data Index: 1097922 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4473. Min Act: -0.0001

Data Index: 233877 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4267. Min Act: -0.0001

Data Index: 1353402 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4390. Min Act: -0.0001

Data Index: 1170736 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4137. Min Act: -0.0001

Data Index: 1265348 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4285. Min Act: -0.0001

Data Index: 259085 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4271. Min Act: -0.0001

Data Index: 742510 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4113. Min Act: -0.0001

Data Index: 1014869 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1047688 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.3952. Min Act: -0.0001

Data Index: 969109 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4284. Min Act: -0.0001

Data Index: 836169 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4305. Min Act: -0.0001

Data Index: 170640 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4244. Min Act: -0.0001

Data Index: 783757 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4227. Min Act: -0.0001

Data Index: 811736 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.3988. Min Act: -0.0001

Data Index: 1134115 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.3971. Min Act: -0.0001

Data Index: 655948 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4095. Min Act: -0.0001

Data Index: 308970 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.5052. Min Range: -0.5052

Max Act: 0.4075. Min Act: -0.0001

Data Index: 788810 (C4 (Web Text))

Max Activating Token Index: 5