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

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

Neuron 1623 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: 2.3641. Min Range: -2.3641

Max Act: 2.3641. Min Act: -0.0000

Data Index: 501025 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.3641. Min Range: -2.3641

Max Act: 2.0997. Min Act: -0.0000

Data Index: 294547 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.3641. Min Range: -2.3641

Max Act: 2.1281. Min Act: -0.0000

Data Index: 1182032 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.9521. Min Act: -0.0000

Data Index: 609467 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.8182. Min Act: -0.0000

Data Index: 977793 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.9116. Min Act: -0.0000

Data Index: 1034023 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 2.3641. Min Range: -2.3641

Max Act: 2.0155. Min Act: -0.0000

Data Index: 141873 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.7918. Min Act: -0.0000

Data Index: 1177638 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.9926. Min Act: -0.0000

Data Index: 602262 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.8965. Min Act: -0.0000

Data Index: 1351948 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.7728. Min Act: -0.0000

Data Index: 143260 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.4054. Min Act: -0.0000

Data Index: 907160 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.7151. Min Act: -0.0000

Data Index: 974153 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.7052. Min Act: -0.0000

Data Index: 1068221 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6982. Min Act: -0.0000

Data Index: 968523 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.3506. Min Act: -0.0000

Data Index: 19164 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1089728 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6683. Min Act: -0.0000

Data Index: 1291255 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6838. Min Act: -0.0000

Data Index: 406935 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 2.3641. Min Range: -2.3641

Max Act: 1.6543. Min Act: -0.0000

Data Index: 99941 (C4 (Web Text))

Max Activating Token Index: 219