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

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

Neuron 786 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: 0.2518. Min Range: -0.2518

Max Act: 0.2518. Min Act: -0.0001

Data Index: 372805 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2332. Min Act: -0.0001

Data Index: 236619 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2337. Min Act: -0.0001

Data Index: 109100 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2249. Min Act: -0.0001

Data Index: 460416 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2072. Min Act: -0.0001

Data Index: 3678 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2109. Min Act: -0.0001

Data Index: 439095 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2198. Min Act: -0.0001

Data Index: 584508 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2079. Min Act: -0.0001

Data Index: 122463 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1968. Min Act: -0.0001

Data Index: 412257 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2030. Min Act: -0.0001

Data Index: 387985 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2034. Min Act: -0.0001

Data Index: 448963 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1990. Min Act: -0.0001

Data Index: 30398 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1293390 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1202665 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1980. Min Act: -0.0001

Data Index: 663196 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1970. Min Act: -0.0001

Data Index: 161598 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1963. Min Act: -0.0001

Data Index: 380272 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1953. Min Act: -0.0000

Data Index: 593253 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1871. Min Act: -0.0001

Data Index: 478546 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1923. Min Act: -0.0001

Data Index: 970967 (C4 (Web Text))

Max Activating Token Index: 665