Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3597 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.6113. Min Act: -0.0000

Data Index: 767158 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5808. Min Act: -0.0000

Data Index: 696715 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1069282 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5002. Min Act: -0.0000

Data Index: 648277 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5255. Min Act: -0.0000

Data Index: 387168 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4981. Min Act: -0.0000

Data Index: 655936 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1351012 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4958. Min Act: 0.0000

Data Index: 222730 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4666. Min Act: -0.0000

Data Index: 251049 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4630. Min Act: -0.0000

Data Index: 202101 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4858. Min Act: -0.0000

Data Index: 600185 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4637. Min Act: -0.0000

Data Index: 798487 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4330. Min Act: -0.0000

Data Index: 169012 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4503. Min Act: -0.0000

Data Index: 225089 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4295. Min Act: -0.0000

Data Index: 419888 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4394. Min Act: -0.0000

Data Index: 790467 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4235. Min Act: -0.0000

Data Index: 384811 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4339. Min Act: 0.0000

Data Index: 1021067 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4330. Min Act: 0.0001

Data Index: 1279374 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.6113. Min Range: -0.6113

Max Act: 0.4318. Min Act: 0.0001

Data Index: 695582 (C4 (Web Text))

Max Activating Token Index: 762