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

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

Neuron 1976 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: 0.6490. Min Range: -0.6490

Max Act: 0.6490. Min Act: -0.0001

Data Index: 5225 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1351940 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6490. Min Act: -0.0001

Data Index: 336594 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6490. Min Act: -0.0001

Data Index: 162874 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6404. Min Act: -0.0001

Data Index: 1031087 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6230. Min Act: -0.0002

Data Index: 75022 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6062. Min Act: -0.0001

Data Index: 879587 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6191. Min Act: -0.0001

Data Index: 319836 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6105. Min Act: -0.0001

Data Index: 477235 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5982. Min Act: -0.0001

Data Index: 402032 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6071. Min Act: -0.0001

Data Index: 211548 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6070. Min Act: -0.0001

Data Index: 987277 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6025. Min Act: -0.0001

Data Index: 1355530 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5965. Min Act: -0.0001

Data Index: 828690 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1196759 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5979. Min Act: -0.0001

Data Index: 206167 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5820. Min Act: -0.0001

Data Index: 197963 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5857. Min Act: -0.0001

Data Index: 967628 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5776. Min Act: -0.0001

Data Index: 1209797 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5866. Min Act: -0.0001

Data Index: 566994 (C4 (Web Text))

Max Activating Token Index: 16