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

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

Neuron 4991 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: 1.8807. Min Range: -1.8807

Max Act: 1.8807. Min Act: -0.0002

Data Index: 1143017 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.8012. Min Act: -0.0002

Data Index: 397637 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.7982. Min Act: -0.0002

Data Index: 430648 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6894. Min Act: -0.0003

Data Index: 814108 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6621. Min Act: -0.0003

Data Index: 872042 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6547. Min Act: -0.0002

Data Index: 1003220 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6550. Min Act: -0.0002

Data Index: 320880 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6354. Min Act: -0.0003

Data Index: 124183 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6198. Min Act: -0.0002

Data Index: 1075718 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6096. Min Act: -0.0002

Data Index: 607923 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6116. Min Act: -0.0002

Data Index: 1276795 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6106. Min Act: -0.0002

Data Index: 218328 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.5920. Min Act: -0.0002

Data Index: 1050461 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6131. Min Act: -0.0002

Data Index: 993702 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.5632. Min Act: -0.0002

Data Index: 423091 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.5925. Min Act: -0.0002

Data Index: 854039 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.6119. Min Act: -0.0002

Data Index: 2346 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.5880. Min Act: -0.0002

Data Index: 1199820 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.5723. Min Act: -0.0002

Data Index: 1091556 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.8807. Min Range: -1.8807

Max Act: 1.5455. Min Act: -0.0002

Data Index: 147337 (C4 (Web Text))

Max Activating Token Index: 401