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

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

Neuron 3385 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.6096. Min Act: -0.0001

Data Index: 72689 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.4492. Min Act: -0.0001

Data Index: 1209651 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.3725. Min Act: -0.0001

Data Index: 927870 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.3412. Min Act: -0.0001

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.3032. Min Act: -0.0001

Data Index: 292495 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.3033. Min Act: -0.0001

Data Index: 126746 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2951. Min Act: -0.0001

Data Index: 1024240 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2887. Min Act: -0.0001

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2862. Min Act: -0.0001

Data Index: 283066 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2935. Min Act: -0.0001

Data Index: 479461 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2716. Min Act: -0.0000

Data Index: 554954 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1274164 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2774. Min Act: -0.0001

Data Index: 376110 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2879. Min Act: -0.0001

Data Index: 752338 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2674. Min Act: -0.0000

Data Index: 776027 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2399. Min Act: -0.0001

Data Index: 766747 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2811. Min Act: -0.0001

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2891. Min Act: -0.0001

Data Index: 675547 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2629. Min Act: -0.0001

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.6096. Min Range: -0.6096

Max Act: 0.2782. Min Act: -0.0001

Data Index: 784115 (C4 (Web Text))

Max Activating Token Index: 815