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

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

Neuron 4715 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: 2.5694. Min Range: -2.5694

Max Act: 2.5694. Min Act: -0.0002

Data Index: 558141 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 2.5694. Min Range: -2.5694

Max Act: 2.3268. Min Act: -0.0002

Data Index: 633777 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.5694. Min Range: -2.5694

Max Act: 2.4030. Min Act: -0.0002

Data Index: 242540 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 2.5694. Min Range: -2.5694

Max Act: 2.2003. Min Act: -0.0002

Data Index: 510426 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 2.5694. Min Range: -2.5694

Max Act: 2.0892. Min Act: -0.0002

Data Index: 539355 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 2.5694. Min Range: -2.5694

Max Act: 2.0499. Min Act: -0.0002

Data Index: 462178 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 2.5694. Min Range: -2.5694

Max Act: 2.0365. Min Act: -0.0002

Data Index: 1348360 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 2.5694. Min Range: -2.5694

Max Act: 2.0025. Min Act: -0.0002

Data Index: 278456 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.9378. Min Act: -0.0002

Data Index: 1117948 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.9030. Min Act: -0.0002

Data Index: 68304 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.9815. Min Act: -0.0002

Data Index: 210286 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8963. Min Act: -0.0002

Data Index: 594268 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8873. Min Act: -0.0002

Data Index: 27629 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8862. Min Act: -0.0002

Data Index: 1031357 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8765. Min Act: -0.0002

Data Index: 1209722 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8727. Min Act: -0.0002

Data Index: 258897 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8381. Min Act: -0.0002

Data Index: 1023871 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8513. Min Act: -0.0002

Data Index: 438976 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8114. Min Act: -0.0002

Data Index: 758496 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 2.5694. Min Range: -2.5694

Max Act: 1.8316. Min Act: -0.0002

Data Index: 1209807 (C4 (Web Text))

Max Activating Token Index: 116