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

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

Neuron 6058 in Layer 1

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: 1.1867. Min Range: -1.1867

Max Act: 1.1762. Min Act: -0.0002

Data Index: 225594 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1867. Min Act: -0.0002

Data Index: 1343934 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1603. Min Act: -0.0002

Data Index: 1067475 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1697. Min Act: -0.0002

Data Index: 5745 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1593. Min Act: -0.0002

Data Index: 139815 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1573. Min Act: -0.0002

Data Index: 25708 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1340. Min Act: -0.0002

Data Index: 430219 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1286. Min Act: -0.0002

Data Index: 528592 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1564. Min Act: -0.0002

Data Index: 25825 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1301. Min Act: -0.0002

Data Index: 813770 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1303. Min Act: -0.0002

Data Index: 1554062 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1303. Min Act: -0.0002

Data Index: 1601068 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1303. Min Act: -0.0002

Data Index: 1307930 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.0982. Min Act: -0.0002

Data Index: 1475675 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1060. Min Act: -0.0002

Data Index: 542687 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1018. Min Act: -0.0002

Data Index: 504348 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.0948. Min Act: -0.0002

Data Index: 417104 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1148. Min Act: -0.0002

Data Index: 217202 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.1034. Min Act: -0.0002

Data Index: 260173 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.1867. Min Range: -1.1867

Max Act: 1.0797. Min Act: -0.0002

Data Index: 31798 (C4 (Web Text))

Max Activating Token Index: 2