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

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

Neuron 2954 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2591. Min Range: -3.2591

Max Act: 3.2591. Min Act: -0.0001

Data Index: 1516501 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.8152. Min Act: -0.0001

Data Index: 109889 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.6415. Min Act: -0.0000

Data Index: 812490 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.6067. Min Act: -0.0000

Data Index: 724188 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.8303. Min Act: -0.0000

Data Index: 293926 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.6272. Min Act: -0.0001

Data Index: 1471558 (Python Code)

Max Activating Token Index: 449

Text #6

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.6101. Min Act: -0.0000

Data Index: 919096 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.5440. Min Act: -0.0001

Data Index: 837581 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.4801. Min Act: -0.0000

Data Index: 337734 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.5297. Min Act: -0.0000

Data Index: 1081706 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.4475. Min Act: -0.0001

Data Index: 785330 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.3889. Min Act: -0.0000

Data Index: 600988 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.4731. Min Act: -0.0000

Data Index: 953343 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.4679. Min Act: -0.0001

Data Index: 327064 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.4333. Min Act: -0.0001

Data Index: 1634792 (Python Code)

Max Activating Token Index: 217

Text #15

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.3908. Min Act: -0.0001

Data Index: 1523294 (Python Code)

Max Activating Token Index: 234

Text #16

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.4354. Min Act: -0.0001

Data Index: 941029 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.2537. Min Act: -0.0001

Data Index: 1497575 (Python Code)

Max Activating Token Index: 348

Text #18

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.5026. Min Act: -0.0001

Data Index: 1618391 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 3.2591. Min Range: -3.2591

Max Act: 2.4965. Min Act: -0.0001

Data Index: 816084 (C4 (Web Text))

Max Activating Token Index: 845