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

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

Neuron 3339 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: 0.5045. Min Range: -0.5045

Max Act: 0.5045. Min Act: -0.0001

Data Index: 545958 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4979. Min Act: -0.0001

Data Index: 475601 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4972. Min Act: -0.0001

Data Index: 725369 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4933. Min Act: -0.0001

Data Index: 914862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4741. Min Act: -0.0001

Data Index: 7499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4624. Min Act: -0.0001

Data Index: 529050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4641. Min Act: -0.0001

Data Index: 955153 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4633. Min Act: -0.0001

Data Index: 838916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4653. Min Act: -0.0001

Data Index: 636478 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4643. Min Act: -0.0001

Data Index: 1170531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4646. Min Act: -0.0001

Data Index: 532575 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4535. Min Act: -0.0001

Data Index: 821865 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4539. Min Act: -0.0001

Data Index: 830868 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4558. Min Act: -0.0001

Data Index: 1210246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4592. Min Act: -0.0001

Data Index: 202422 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4462. Min Act: -0.0001

Data Index: 333003 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1100098 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4548. Min Act: -0.0001

Data Index: 479937 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4566. Min Act: -0.0001

Data Index: 521062 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4545. Min Act: -0.0001

Data Index: 822990 (C4 (Web Text))

Max Activating Token Index: 1023