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

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

Neuron 3058 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.4492. Min Act: 0.0000

Data Index: 333188 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.4384. Min Act: 0.0001

Data Index: 1081431 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.4380. Min Act: -0.0000

Data Index: 590572 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.4357. Min Act: -0.0000

Data Index: 1039193 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.4036. Min Act: -0.0000

Data Index: 51120 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.2838. Min Act: -0.0000

Data Index: 711474 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.3130. Min Act: -0.0000

Data Index: 579581 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.2810. Min Act: -0.0000

Data Index: 1147395 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1220215 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.3409. Min Act: -0.0000

Data Index: 317762 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1163326 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.3178. Min Act: -0.0000

Data Index: 565018 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.4008. Min Act: -0.0000

Data Index: 80859 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.2837. Min Act: -0.0000

Data Index: 1332842 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.2087. Min Act: -0.0000

Data Index: 231556 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.1904. Min Act: -0.0000

Data Index: 639329 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.2000. Min Act: -0.0000

Data Index: 393973 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.1408. Min Act: -0.0000

Data Index: 200503 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.1268. Min Act: -0.0000

Data Index: 979751 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.1995. Min Act: -0.0000

Data Index: 1225828 (C4 (Web Text))

Max Activating Token Index: 641