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

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

Neuron 2890 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: 1.6486. Min Range: -1.6486

Max Act: 1.6486. Min Act: -0.0002

Data Index: 583812 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.3400. Min Act: -0.0002

Data Index: 809583 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1975. Min Act: -0.0002

Data Index: 20870 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1932. Min Act: -0.0002

Data Index: 1276609 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.2018. Min Act: -0.0002

Data Index: 1293116 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 621615 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 463458 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 273275 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 539065 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 431104 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 135788 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 403545 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 184588 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 56138 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 39167 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 697676 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 274087 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 204881 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 69970 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1665. Min Act: -0.0002

Data Index: 327381 (C4 (Web Text))

Max Activating Token Index: 4