Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2072 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4786. Min Act: -0.0001

Data Index: 1086284 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4311. Min Act: -0.0000

Data Index: 999933 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3857. Min Act: -0.0001

Data Index: 1309582 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3896. Min Act: -0.0001

Data Index: 399820 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.4044. Min Act: -0.0001

Data Index: 477758 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3603. Min Act: -0.0001

Data Index: 1054431 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1337523 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3597. Min Act: -0.0001

Data Index: 985998 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3620. Min Act: -0.0001

Data Index: 134653 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3561. Min Act: -0.0001

Data Index: 242053 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3388. Min Act: -0.0000

Data Index: 324282 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3134. Min Act: -0.0001

Data Index: 1241531 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3289. Min Act: -0.0001

Data Index: 469788 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3293. Min Act: -0.0001

Data Index: 1228324 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3266. Min Act: -0.0001

Data Index: 1177067 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3262. Min Act: -0.0001

Data Index: 2054 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3241. Min Act: -0.0001

Data Index: 285905 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3152. Min Act: -0.0001

Data Index: 1054798 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1046974 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.4786. Min Range: -0.4786

Max Act: 0.3130. Min Act: -0.0001

Data Index: 716760 (C4 (Web Text))

Max Activating Token Index: 686