Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2005 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.6683. Min Act: -0.0003

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.5026. Min Act: -0.0003

Data Index: 1647089 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.3951. Min Act: -0.0003

Data Index: 129750 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.4071. Min Act: -0.0003

Data Index: 1575383 (Python Code)

Max Activating Token Index: 868

Text #4

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.3404. Min Act: -0.0003

Data Index: 674424 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.3282. Min Act: -0.0003

Data Index: 213557 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.3195. Min Act: -0.0003

Data Index: 1090252 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.3140. Min Act: -0.0003

Data Index: 617072 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2895. Min Act: -0.0003

Data Index: 365845 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2856. Min Act: -0.0004

Data Index: 378487 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2963. Min Act: -0.0003

Data Index: 1302787 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2939. Min Act: -0.0003

Data Index: 1011090 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2955. Min Act: -0.0003

Data Index: 375550 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2904. Min Act: -0.0003

Data Index: 707564 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2900. Min Act: -0.0003

Data Index: 1304675 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2808. Min Act: -0.0004

Data Index: 380521 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2827. Min Act: -0.0003

Data Index: 288306 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2819. Min Act: -0.0003

Data Index: 1328434 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2788. Min Act: -0.0003

Data Index: 507252 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.6683. Min Range: -0.6683

Max Act: 0.2859. Min Act: -0.0003

Data Index: 716133 (C4 (Web Text))

Max Activating Token Index: 267