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

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

Neuron 887 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1124983 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.3302. Min Act: 0.0000

Data Index: 1345993 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1305868 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1098511 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.3071. Min Act: -0.0001

Data Index: 27834 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2967. Min Act: -0.0001

Data Index: 599457 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2952. Min Act: -0.0001

Data Index: 1096320 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2971. Min Act: -0.0001

Data Index: 4556 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2943. Min Act: -0.0001

Data Index: 505653 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1185701 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2894. Min Act: 0.0000

Data Index: 1096067 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2908. Min Act: -0.0001

Data Index: 234047 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2866. Min Act: -0.0001

Data Index: 657497 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2949. Min Act: -0.0001

Data Index: 125170 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2707. Min Act: -0.0001

Data Index: 855767 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2763. Min Act: 0.0000

Data Index: 390122 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1013136 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2629. Min Act: 0.0000

Data Index: 669717 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2726. Min Act: -0.0000

Data Index: 722744 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.3558. Min Range: -0.3558

Max Act: 0.2791. Min Act: -0.0000

Data Index: 280570 (C4 (Web Text))

Max Activating Token Index: 188