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

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

Neuron 3409 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: 1.9865. Min Range: -1.9865

Max Act: 1.9865. Min Act: -0.0002

Data Index: 1157171 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.9533. Min Act: -0.0002

Data Index: 767363 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.9022. Min Act: -0.0002

Data Index: 744160 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8901. Min Act: -0.0002

Data Index: 772106 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.9067. Min Act: -0.0002

Data Index: 561094 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8393. Min Act: -0.0002

Data Index: 580712 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8267. Min Act: -0.0002

Data Index: 1177674 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8120. Min Act: -0.0002

Data Index: 986440 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8597. Min Act: -0.0002

Data Index: 369615 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.7850. Min Act: -0.0002

Data Index: 810541 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8370. Min Act: -0.0002

Data Index: 1098186 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.7861. Min Act: -0.0002

Data Index: 162601 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8205. Min Act: -0.0002

Data Index: 168484 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.7969. Min Act: -0.0002

Data Index: 723966 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.7831. Min Act: -0.0002

Data Index: 206959 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.8133. Min Act: -0.0002

Data Index: 323155 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.7661. Min Act: -0.0003

Data Index: 1035211 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.7381. Min Act: -0.0002

Data Index: 83483 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.7117. Min Act: -0.0003

Data Index: 110671 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.9865. Min Range: -1.9865

Max Act: 1.6734. Min Act: -0.0002

Data Index: 155780 (C4 (Web Text))

Max Activating Token Index: 11