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

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

Neuron 4673 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: 2.2427. Min Range: -2.2427

Max Act: 2.2427. Min Act: -0.0002

Data Index: 93747 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 2.2427. Min Range: -2.2427

Max Act: 2.0622. Min Act: -0.0002

Data Index: 1349774 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 2.2427. Min Range: -2.2427

Max Act: 2.0407. Min Act: -0.0002

Data Index: 503593 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 2.2427. Min Range: -2.2427

Max Act: 2.0729. Min Act: -0.0002

Data Index: 605614 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.9786. Min Act: -0.0002

Data Index: 1210196 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.9800. Min Act: -0.0002

Data Index: 451302 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.9643. Min Act: -0.0002

Data Index: 290201 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.9011. Min Act: -0.0002

Data Index: 751617 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8810. Min Act: -0.0002

Data Index: 1319049 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.9110. Min Act: -0.0002

Data Index: 1240257 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.9702. Min Act: -0.0002

Data Index: 189759 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8771. Min Act: -0.0002

Data Index: 356208 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.9086. Min Act: -0.0002

Data Index: 777961 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8670. Min Act: -0.0002

Data Index: 60611 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8504. Min Act: -0.0002

Data Index: 338396 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8458. Min Act: -0.0002

Data Index: 656031 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8505. Min Act: -0.0002

Data Index: 922754 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8210. Min Act: -0.0002

Data Index: 576976 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.7948. Min Act: -0.0002

Data Index: 185777 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 2.2427. Min Range: -2.2427

Max Act: 1.8128. Min Act: -0.0002

Data Index: 418150 (C4 (Web Text))

Max Activating Token Index: 826