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

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

Neuron 5370 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: 2.0097. Min Range: -2.0097

Max Act: 2.0097. Min Act: -0.0002

Data Index: 590012 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.7330. Min Act: -0.0002

Data Index: 1120576 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.7330. Min Act: -0.0002

Data Index: 998588 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.7330. Min Act: -0.0002

Data Index: 643810 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.7330. Min Act: -0.0002

Data Index: 496858 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.7330. Min Act: -0.0002

Data Index: 1258444 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.7330. Min Act: -0.0002

Data Index: 408375 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.6512. Min Act: -0.0002

Data Index: 209798 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.6547. Min Act: -0.0002

Data Index: 958120 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.6144. Min Act: -0.0002

Data Index: 281389 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.5647. Min Act: -0.0002

Data Index: 1222931 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.5894. Min Act: -0.0002

Data Index: 659080 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.5894. Min Act: -0.0002

Data Index: 497264 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.5091. Min Act: -0.0002

Data Index: 611117 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.5718. Min Act: -0.0002

Data Index: 1147948 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.5107. Min Act: -0.0002

Data Index: 32753 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.4745. Min Act: -0.0002

Data Index: 865188 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.4356. Min Act: -0.0002

Data Index: 58339 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.4416. Min Act: -0.0002

Data Index: 846935 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 2.0097. Min Range: -2.0097

Max Act: 1.4370. Min Act: -0.0002

Data Index: 647947 (C4 (Web Text))

Max Activating Token Index: 3