Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1053 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.4029. Min Act: -0.0001

Data Index: 827127 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3192. Min Act: -0.0001

Data Index: 315355 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1020205 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3283. Min Act: -0.0001

Data Index: 627689 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3169. Min Act: -0.0001

Data Index: 45427 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3217. Min Act: -0.0001

Data Index: 559272 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3081. Min Act: -0.0001

Data Index: 215639 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2969. Min Act: -0.0001

Data Index: 859663 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1077527 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3217. Min Act: -0.0001

Data Index: 996988 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2896. Min Act: -0.0001

Data Index: 567322 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2785. Min Act: -0.0001

Data Index: 541598 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2781. Min Act: -0.0001

Data Index: 695652 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.3032. Min Act: -0.0001

Data Index: 1113418 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2947. Min Act: -0.0001

Data Index: 58681 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2837. Min Act: -0.0001

Data Index: 593372 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2748. Min Act: -0.0001

Data Index: 239607 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2921. Min Act: -0.0001

Data Index: 1235035 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2808. Min Act: -0.0001

Data Index: 512424 (C4 (Web Text))

Max Activating Token Index: 245

Text #19

Max Range: 0.4029. Min Range: -0.4029

Max Act: 0.2726. Min Act: -0.0001

Data Index: 472032 (C4 (Web Text))

Max Activating Token Index: 515