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

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

Neuron 3619 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: 0.9458. Min Range: -0.9458

Max Act: 0.9458. Min Act: -0.0002

Data Index: 539529 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.9329. Min Act: -0.0002

Data Index: 58784 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.9295. Min Act: -0.0002

Data Index: 496361 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.9010. Min Act: -0.0002

Data Index: 321184 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8865. Min Act: -0.0002

Data Index: 922347 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8930. Min Act: -0.0002

Data Index: 945889 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8769. Min Act: -0.0002

Data Index: 880802 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8737. Min Act: -0.0002

Data Index: 454070 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8900. Min Act: -0.0002

Data Index: 977353 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8641. Min Act: -0.0002

Data Index: 14302 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8722. Min Act: -0.0002

Data Index: 1001229 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8546. Min Act: -0.0002

Data Index: 322765 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8766. Min Act: -0.0002

Data Index: 1002159 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8624. Min Act: -0.0002

Data Index: 476651 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8599. Min Act: -0.0002

Data Index: 885483 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8522. Min Act: -0.0003

Data Index: 889250 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8329. Min Act: -0.0002

Data Index: 1216395 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8607. Min Act: -0.0002

Data Index: 467323 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8414. Min Act: -0.0002

Data Index: 298256 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.8432. Min Act: -0.0002

Data Index: 1315545 (C4 (Web Text))

Max Activating Token Index: 79