Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7936. Min Act: -0.0000

Data Index: 578184 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.7309. Min Act: -0.0001

Data Index: 989364 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6456. Min Act: -0.0001

Data Index: 269830 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6119. Min Act: -0.0001

Data Index: 496281 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1147664 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5899. Min Act: -0.0000

Data Index: 400930 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5817. Min Act: -0.0001

Data Index: 251354 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1030001 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1434329 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5676. Min Act: -0.0001

Data Index: 202638 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5705. Min Act: -0.0001

Data Index: 894301 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1191496 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5596. Min Act: -0.0001

Data Index: 756505 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1109781 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5511. Min Act: -0.0000

Data Index: 176240 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1267907 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5410. Min Act: -0.0000

Data Index: 709035 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5336. Min Act: -0.0001

Data Index: 153259 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5359. Min Act: -0.0001

Data Index: 510768 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.7936. Min Range: -0.7936

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1028264 (C4 (Web Text))

Max Activating Token Index: 618