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

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

Neuron 727 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.3088. Min Act: -0.0001

Data Index: 508532 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2398. Min Act: -0.0001

Data Index: 469117 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1250746 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2393. Min Act: -0.0001

Data Index: 347789 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1988. Min Act: -0.0001

Data Index: 708543 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1181520 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.2066. Min Act: -0.0001

Data Index: 1239291 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1906. Min Act: -0.0001

Data Index: 99116 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1946. Min Act: -0.0001

Data Index: 792855 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1819. Min Act: -0.0001

Data Index: 775709 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1269160 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1840. Min Act: -0.0001

Data Index: 760527 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1833. Min Act: -0.0001

Data Index: 717115 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1974. Min Act: -0.0001

Data Index: 345328 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1965. Min Act: -0.0001

Data Index: 1247608 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1254551 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1933. Min Act: -0.0001

Data Index: 1314074 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1777. Min Act: -0.0001

Data Index: 884351 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1960. Min Act: -0.0001

Data Index: 278462 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.3088. Min Range: -0.3088

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1058291 (C4 (Web Text))

Max Activating Token Index: 560