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

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

Neuron 4870 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: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 906056 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0003

Data Index: 785293 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0003

Data Index: 369845 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1159524 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0003

Data Index: 626259 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 827235 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 996648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 464075 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 811089 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0003

Data Index: 1236521 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 625045 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1108239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1639033 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1418091 (Python Code)

Max Activating Token Index: 85

Text #14

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1060722 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 380112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1653644 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 29531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 979574 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1496719 (Python Code)

Max Activating Token Index: 36