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

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

Neuron 1606 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3117. Min Act: -0.0001

Data Index: 707450 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3351. Min Act: -0.0001

Data Index: 120066 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.3046. Min Act: -0.0001

Data Index: 1287183 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2877. Min Act: -0.0001

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2968. Min Act: -0.0001

Data Index: 275237 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2442. Min Act: -0.0001

Data Index: 498892 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2621. Min Act: -0.0001

Data Index: 1337545 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2817. Min Act: -0.0001

Data Index: 771290 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1254523 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2774. Min Act: -0.0001

Data Index: 80785 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2422. Min Act: -0.0001

Data Index: 869679 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2590. Min Act: -0.0001

Data Index: 178842 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2702. Min Act: -0.0001

Data Index: 112638 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1046040 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2284. Min Act: -0.0001

Data Index: 529346 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2077. Min Act: -0.0001

Data Index: 280260 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2265. Min Act: -0.0001

Data Index: 350262 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2343. Min Act: -0.0001

Data Index: 870934 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1029793 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.3351. Min Range: -0.3351

Max Act: 0.2431. Min Act: -0.0001

Data Index: 1119927 (C4 (Web Text))

Max Activating Token Index: 902