Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 499 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0006

Data Index: 690071 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1186480 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1137085 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1251519 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0057. Min Act: -0.0006

Data Index: 881697 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0007

Data Index: 929017 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0006

Data Index: 642378 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0006

Data Index: 325876 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0006

Data Index: 167946 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0006

Data Index: 488790 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0006

Data Index: 887421 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0006

Data Index: 392368 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0006

Data Index: 252053 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1079353 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0006

Data Index: 455652 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1289909 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0049. Min Act: -0.0006

Data Index: 831568 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0049. Min Act: -0.0006

Data Index: 360396 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0049. Min Act: -0.0007

Data Index: 82354 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0049. Min Act: -0.0006

Data Index: 345139 (C4 (Web Text))

Max Activating Token Index: 799