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

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

Neuron 5146 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: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0002

Data Index: 1061954 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6461. Min Act: -0.0002

Data Index: 1015706 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6350. Min Act: -0.0002

Data Index: 487951 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6311. Min Act: -0.0002

Data Index: 1215017 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6279. Min Act: -0.0002

Data Index: 206011 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6299. Min Act: -0.0002

Data Index: 1281827 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6209. Min Act: -0.0002

Data Index: 117605 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6210. Min Act: -0.0002

Data Index: 964025 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6386. Min Act: -0.0002

Data Index: 838497 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.6175. Min Act: -0.0002

Data Index: 539180 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5949. Min Act: -0.0002

Data Index: 1353664 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5833. Min Act: -0.0002

Data Index: 640003 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5925. Min Act: -0.0002

Data Index: 493050 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5757. Min Act: -0.0002

Data Index: 250998 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5760. Min Act: -0.0002

Data Index: 848011 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5774. Min Act: -0.0002

Data Index: 56346 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5731. Min Act: -0.0002

Data Index: 1090616 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5731. Min Act: -0.0002

Data Index: 547746 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5649. Min Act: -0.0002

Data Index: 858436 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5696. Min Act: -0.0002

Data Index: 1200095 (C4 (Web Text))

Max Activating Token Index: 446