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

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

Neuron 4700 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1641. Min Range: -7.1641

Max Act: 7.1641. Min Act: -0.0000

Data Index: 1223847 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.9492. Min Act: -0.0000

Data Index: 1227713 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.9050. Min Act: -0.0000

Data Index: 604085 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.6248. Min Act: -0.0000

Data Index: 233537 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.5681. Min Act: -0.0000

Data Index: 511116 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.4649. Min Act: -0.0000

Data Index: 1027820 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.2628. Min Act: -0.0000

Data Index: 630911 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.3774. Min Act: -0.0000

Data Index: 773362 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.3472. Min Act: -0.0000

Data Index: 409879 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.2494. Min Act: -0.0000

Data Index: 546968 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 7.1641. Min Range: -7.1641

Max Act: 6.5698. Min Act: -0.0000

Data Index: 754826 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.8097. Min Act: -0.0000

Data Index: 825577 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.7624. Min Act: -0.0000

Data Index: 128642 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.7261. Min Act: -0.0000

Data Index: 141439 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.6765. Min Act: -0.0000

Data Index: 231415 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.7695. Min Act: -0.0000

Data Index: 1006933 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.7355. Min Act: 0.0000

Data Index: 507878 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.7126. Min Act: -0.0000

Data Index: 776636 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.8722. Min Act: -0.0000

Data Index: 162515 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 7.1641. Min Range: -7.1641

Max Act: 5.7819. Min Act: -0.0000

Data Index: 988527 (C4 (Web Text))

Max Activating Token Index: 865