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

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

Neuron 421 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: 3.3101. Min Range: -3.3101

Max Act: 3.2932. Min Act: -0.0000

Data Index: 536064 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 3.3101. Min Range: -3.3101

Max Act: 3.3101. Min Act: -0.0000

Data Index: 1241181 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 3.3101. Min Range: -3.3101

Max Act: 3.0882. Min Act: -0.0000

Data Index: 771040 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 3.3101. Min Range: -3.3101

Max Act: 3.0717. Min Act: -0.0000

Data Index: 310390 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 3.3101. Min Range: -3.3101

Max Act: 3.1465. Min Act: -0.0000

Data Index: 956562 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.8380. Min Act: -0.0000

Data Index: 768648 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.8835. Min Act: -0.0000

Data Index: 301260 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.7258. Min Act: -0.0000

Data Index: 45581 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.8044. Min Act: -0.0000

Data Index: 11983 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.7602. Min Act: -0.0000

Data Index: 1289030 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.7393. Min Act: -0.0000

Data Index: 992979 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.7106. Min Act: -0.0000

Data Index: 554169 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.6702. Min Act: -0.0000

Data Index: 970479 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.5385. Min Act: -0.0000

Data Index: 345097 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.8233. Min Act: -0.0000

Data Index: 179825 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.5084. Min Act: -0.0000

Data Index: 220640 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.5843. Min Act: -0.0000

Data Index: 294021 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.6174. Min Act: -0.0000

Data Index: 62593 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.5754. Min Act: -0.0000

Data Index: 58978 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 3.3101. Min Range: -3.3101

Max Act: 2.5724. Min Act: -0.0000

Data Index: 1048276 (C4 (Web Text))

Max Activating Token Index: 953