Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5758 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.7647. Min Act: -0.0001

Data Index: 220260 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.6070. Min Act: -0.0001

Data Index: 732059 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5904. Min Act: -0.0000

Data Index: 251462 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1257597 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5576. Min Act: -0.0001

Data Index: 793658 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5454. Min Act: -0.0001

Data Index: 829150 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5314. Min Act: -0.0000

Data Index: 842650 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5046. Min Act: -0.0001

Data Index: 901006 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5127. Min Act: -0.0001

Data Index: 1031480 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1205948 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5079. Min Act: -0.0001

Data Index: 851699 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.5123. Min Act: -0.0000

Data Index: 495021 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4693. Min Act: -0.0000

Data Index: 340149 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4546. Min Act: -0.0000

Data Index: 532548 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4478. Min Act: -0.0001

Data Index: 259585 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4392. Min Act: -0.0001

Data Index: 457570 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4520. Min Act: -0.0000

Data Index: 195799 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4581. Min Act: -0.0001

Data Index: 939687 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4363. Min Act: -0.0001

Data Index: 1564773 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 0.7647. Min Range: -0.7647

Max Act: 0.4376. Min Act: -0.0001

Data Index: 168934 (C4 (Web Text))

Max Activating Token Index: 281