Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3971. Min Act: -0.0000

Data Index: 981862 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3775. Min Act: -0.0000

Data Index: 1589701 (Python Code)

Max Activating Token Index: 832

Text #2

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1057008 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3676. Min Act: -0.0000

Data Index: 441074 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3624. Min Act: -0.0000

Data Index: 1585326 (Python Code)

Max Activating Token Index: 687

Text #5

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1620729 (Python Code)

Max Activating Token Index: 772

Text #6

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1562167 (Python Code)

Max Activating Token Index: 469

Text #7

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1478187 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1495979 (Python Code)

Max Activating Token Index: 339

Text #9

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3243. Min Act: -0.0000

Data Index: 483436 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2740. Min Act: -0.0000

Data Index: 511021 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1616631 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1574299 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3103. Min Act: -0.0000

Data Index: 883919 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1570961 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3030. Min Act: -0.0000

Data Index: 962385 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1124789 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2970. Min Act: -0.0000

Data Index: 407077 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1114865 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2637. Min Act: -0.0000

Data Index: 616221 (C4 (Web Text))

Max Activating Token Index: 920