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

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

Neuron 118 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: 2.4889. Min Range: -2.4889

Max Act: 2.4320. Min Act: -0.0000

Data Index: 996820 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.3972. Min Act: -0.0000

Data Index: 363383 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.4889. Min Act: -0.0000

Data Index: 215976 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.2400. Min Act: -0.0000

Data Index: 819295 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.3251. Min Act: -0.0000

Data Index: 528295 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.0620. Min Act: -0.0000

Data Index: 154537 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.0988. Min Act: -0.0000

Data Index: 676889 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.1255. Min Act: -0.0000

Data Index: 524664 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.0009. Min Act: -0.0000

Data Index: 568294 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.8939. Min Act: -0.0000

Data Index: 632189 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.9348. Min Act: -0.0000

Data Index: 840011 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 2.4889. Min Range: -2.4889

Max Act: 2.0092. Min Act: -0.0000

Data Index: 28181 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.9834. Min Act: -0.0000

Data Index: 301486 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.9943. Min Act: -0.0000

Data Index: 676122 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.9947. Min Act: -0.0000

Data Index: 51534 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.7769. Min Act: -0.0000

Data Index: 1081705 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.8424. Min Act: -0.0000

Data Index: 840007 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.7933. Min Act: -0.0000

Data Index: 760226 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.7880. Min Act: -0.0000

Data Index: 858283 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 2.4889. Min Range: -2.4889

Max Act: 1.7818. Min Act: -0.0000

Data Index: 159542 (C4 (Web Text))

Max Activating Token Index: 442