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

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

Neuron 332 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: 0.9904. Min Range: -0.9904

Max Act: 0.9904. Min Act: -0.0002

Data Index: 956207 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9733. Min Act: -0.0002

Data Index: 949687 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9758. Min Act: -0.0002

Data Index: 178007 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9451. Min Act: -0.0002

Data Index: 578343 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9003. Min Act: -0.0002

Data Index: 747549 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9004. Min Act: -0.0003

Data Index: 1306124 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.9052. Min Act: -0.0002

Data Index: 234526 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8812. Min Act: -0.0002

Data Index: 290132 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8777. Min Act: -0.0002

Data Index: 1305595 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8889. Min Act: -0.0002

Data Index: 819362 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8755. Min Act: -0.0002

Data Index: 23311 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8744. Min Act: -0.0002

Data Index: 573606 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8721. Min Act: -0.0002

Data Index: 813548 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8618. Min Act: -0.0002

Data Index: 1072207 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8656. Min Act: -0.0002

Data Index: 1108945 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8195. Min Act: -0.0002

Data Index: 286077 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8629. Min Act: -0.0002

Data Index: 1061183 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8237. Min Act: -0.0002

Data Index: 847138 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8257. Min Act: -0.0002

Data Index: 556618 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.9904. Min Range: -0.9904

Max Act: 0.8217. Min Act: -0.0002

Data Index: 863693 (C4 (Web Text))

Max Activating Token Index: 328