Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1054 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0001

Data Index: 857527 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3231. Min Act: -0.0001

Data Index: 1069308 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3111. Min Act: -0.0001

Data Index: 918662 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3119. Min Act: -0.0001

Data Index: 122633 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3016. Min Act: -0.0001

Data Index: 556736 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2870. Min Act: -0.0001

Data Index: 218712 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2816. Min Act: -0.0001

Data Index: 1274754 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2897. Min Act: -0.0001

Data Index: 447554 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2978. Min Act: -0.0001

Data Index: 844070 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2866. Min Act: -0.0001

Data Index: 1096327 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2575. Min Act: -0.0001

Data Index: 727470 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2730. Min Act: -0.0001

Data Index: 438580 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2789. Min Act: -0.0001

Data Index: 876350 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2869. Min Act: -0.0001

Data Index: 297988 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2863. Min Act: -0.0001

Data Index: 273516 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1067943 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2556. Min Act: -0.0001

Data Index: 984933 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2640. Min Act: -0.0001

Data Index: 752370 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2815. Min Act: -0.0001

Data Index: 292938 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2726. Min Act: -0.0001

Data Index: 942470 (C4 (Web Text))

Max Activating Token Index: 383