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

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

Neuron 3854 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: 7.1937. Min Range: -7.1937

Max Act: 7.0914. Min Act: -0.0000

Data Index: 643297 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 7.1937. Min Range: -7.1937

Max Act: 7.1937. Min Act: -0.0000

Data Index: 708827 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.9676. Min Act: -0.0000

Data Index: 488521 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.7578. Min Act: -0.0000

Data Index: 314434 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.7485. Min Act: -0.0000

Data Index: 160932 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.7628. Min Act: -0.0000

Data Index: 463542 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.4254. Min Act: -0.0000

Data Index: 658339 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.4165. Min Act: -0.0000

Data Index: 221306 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.4140. Min Act: -0.0000

Data Index: 1063752 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.7498. Min Act: -0.0000

Data Index: 1122532 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.3424. Min Act: -0.0000

Data Index: 649159 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.2778. Min Act: -0.0000

Data Index: 1026237 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.0821. Min Act: -0.0000

Data Index: 81169 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.4114. Min Act: -0.0000

Data Index: 32753 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.2231. Min Act: -0.0000

Data Index: 1210623 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.2278. Min Act: -0.0000

Data Index: 266922 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.1890. Min Act: -0.0000

Data Index: 1287975 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.3598. Min Act: -0.0000

Data Index: 216387 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.2457. Min Act: -0.0000

Data Index: 1074480 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 7.1937. Min Range: -7.1937

Max Act: 6.0347. Min Act: -0.0000

Data Index: 1217413 (C4 (Web Text))

Max Activating Token Index: 293