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

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

Neuron 1073 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2924. Min Range: -2.2924

Max Act: 2.2550. Min Act: -0.0000

Data Index: 125901 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 2.2924. Min Range: -2.2924

Max Act: 2.2924. Min Act: -0.0000

Data Index: 644571 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 2.2924. Min Range: -2.2924

Max Act: 2.0042. Min Act: -0.0000

Data Index: 1044178 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 2.2924. Min Range: -2.2924

Max Act: 2.2648. Min Act: -0.0001

Data Index: 968380 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 2.2924. Min Range: -2.2924

Max Act: 2.0312. Min Act: -0.0001

Data Index: 1229121 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.8988. Min Act: -0.0000

Data Index: 799692 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.6430. Min Act: -0.0001

Data Index: 1154468 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.5961. Min Act: -0.0001

Data Index: 448905 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.4541. Min Act: -0.0000

Data Index: 73545 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.5233. Min Act: -0.0000

Data Index: 1140287 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.5149. Min Act: -0.0000

Data Index: 44050 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.5970. Min Act: -0.0000

Data Index: 933809 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.7019. Min Act: -0.0000

Data Index: 417480 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.5790. Min Act: -0.0000

Data Index: 119030 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.5155. Min Act: -0.0001

Data Index: 836643 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.5825. Min Act: -0.0001

Data Index: 67086 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.2887. Min Act: -0.0001

Data Index: 723111 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.4574. Min Act: -0.0001

Data Index: 926896 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.4139. Min Act: -0.0001

Data Index: 440176 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 2.2924. Min Range: -2.2924

Max Act: 1.4063. Min Act: -0.0001

Data Index: 813058 (C4 (Web Text))

Max Activating Token Index: 771