Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3882 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.7882. Min Act: -0.0000

Data Index: 142600 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.6376. Min Act: -0.0000

Data Index: 143082 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.6417. Min Act: -0.0000

Data Index: 503204 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1176910 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.5465. Min Act: -0.0000

Data Index: 706841 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.5425. Min Act: -0.0000

Data Index: 83834 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.5050. Min Act: -0.0000

Data Index: 762664 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.5410. Min Act: -0.0000

Data Index: 581108 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.5185. Min Act: -0.0000

Data Index: 625554 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4693. Min Act: -0.0000

Data Index: 155700 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1191194 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4665. Min Act: -0.0000

Data Index: 672575 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4418. Min Act: -0.0000

Data Index: 289539 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4471. Min Act: -0.0000

Data Index: 352077 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4590. Min Act: -0.0000

Data Index: 779299 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1056275 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4186. Min Act: -0.0000

Data Index: 904251 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4456. Min Act: -0.0000

Data Index: 376885 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4320. Min Act: -0.0000

Data Index: 856378 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.7882. Min Range: -0.7882

Max Act: 0.4246. Min Act: -0.0000

Data Index: 741382 (C4 (Web Text))

Max Activating Token Index: 868