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

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

Neuron 4287 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: 1.0060. Min Range: -1.0060

Max Act: 1.0060. Min Act: -0.0002

Data Index: 1147150 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9849. Min Act: -0.0002

Data Index: 1151842 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9737. Min Act: -0.0002

Data Index: 266612 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9905. Min Act: -0.0002

Data Index: 987928 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9618. Min Act: -0.0002

Data Index: 1343321 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9694. Min Act: -0.0002

Data Index: 30718 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9695. Min Act: -0.0002

Data Index: 740485 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9344. Min Act: -0.0002

Data Index: 543996 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9434. Min Act: -0.0003

Data Index: 498024 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9223. Min Act: -0.0002

Data Index: 1312322 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9300. Min Act: -0.0002

Data Index: 631799 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9011. Min Act: -0.0002

Data Index: 358981 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9088. Min Act: -0.0002

Data Index: 1227472 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9117. Min Act: -0.0002

Data Index: 243449 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9003. Min Act: -0.0002

Data Index: 505848 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9141. Min Act: -0.0002

Data Index: 916736 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9094. Min Act: -0.0002

Data Index: 852552 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9168. Min Act: -0.0002

Data Index: 1187594 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9080. Min Act: -0.0002

Data Index: 449101 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.0060. Min Range: -1.0060

Max Act: 0.9013. Min Act: -0.0002

Data Index: 1305466 (C4 (Web Text))

Max Activating Token Index: 36