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

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

Neuron 4875 in Layer 0

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: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1075490 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0993. Min Act: -0.0001

Data Index: 854816 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1112957 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1097481 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0978. Min Act: -0.0001

Data Index: 676337 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0963. Min Act: -0.0001

Data Index: 827489 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0900. Min Act: -0.0001

Data Index: 338457 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0907. Min Act: -0.0001

Data Index: 119004 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0877. Min Act: -0.0001

Data Index: 523480 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0867. Min Act: -0.0001

Data Index: 34978 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0884. Min Act: -0.0001

Data Index: 256002 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1125995 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1140023 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1156052 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1349749 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0848. Min Act: -0.0001

Data Index: 742955 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1261182 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1357734 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1323540 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0825. Min Act: -0.0001

Data Index: 91767 (C4 (Web Text))

Max Activating Token Index: 91