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

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

Neuron 697 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5857. Min Act: -0.0000

Data Index: 197678 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.6035. Min Act: -0.0000

Data Index: 360810 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5687. Min Act: -0.0000

Data Index: 536124 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5798. Min Act: -0.0000

Data Index: 533944 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5971. Min Act: -0.0000

Data Index: 480262 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5867. Min Act: -0.0000

Data Index: 308640 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5470. Min Act: -0.0000

Data Index: 404444 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1249338 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5257. Min Act: -0.0000

Data Index: 935973 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5063. Min Act: -0.0000

Data Index: 576780 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4989. Min Act: -0.0000

Data Index: 422684 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5024. Min Act: -0.0000

Data Index: 410938 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5064. Min Act: -0.0000

Data Index: 335819 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4600. Min Act: -0.0000

Data Index: 983131 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1106762 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1030121 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1184747 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4912. Min Act: -0.0000

Data Index: 925729 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1198635 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.6035. Min Range: -0.6035

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1004677 (C4 (Web Text))

Max Activating Token Index: 944