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

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

Neuron 1628 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: 0.8660. Min Range: -0.8660

Max Act: 0.8660. Min Act: -0.0002

Data Index: 402256 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6780. Min Act: -0.0002

Data Index: 1342339 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6580. Min Act: -0.0002

Data Index: 12465 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6266. Min Act: -0.0002

Data Index: 116718 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.6056. Min Act: -0.0002

Data Index: 1193344 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5969. Min Act: -0.0002

Data Index: 1173229 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5839. Min Act: -0.0002

Data Index: 1283771 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5718. Min Act: -0.0002

Data Index: 212237 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5431. Min Act: -0.0002

Data Index: 491240 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5503. Min Act: -0.0002

Data Index: 764452 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5520. Min Act: -0.0002

Data Index: 893935 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5381. Min Act: -0.0002

Data Index: 504588 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5206. Min Act: -0.0002

Data Index: 589448 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5174. Min Act: -0.0002

Data Index: 378467 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5236. Min Act: -0.0002

Data Index: 170785 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5320. Min Act: -0.0002

Data Index: 750009 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5134. Min Act: -0.0002

Data Index: 1100190 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5159. Min Act: -0.0002

Data Index: 687345 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5002. Min Act: -0.0002

Data Index: 399293 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.8660. Min Range: -0.8660

Max Act: 0.5076. Min Act: -0.0002

Data Index: 1114877 (C4 (Web Text))

Max Activating Token Index: 2