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

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

Neuron 1136 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.3025. Min Act: -0.0001

Data Index: 621043 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2664. Min Act: -0.0001

Data Index: 275862 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2320. Min Act: -0.0001

Data Index: 1650147 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2453. Min Act: -0.0001

Data Index: 1377291 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2488. Min Act: -0.0001

Data Index: 305608 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2100. Min Act: -0.0001

Data Index: 622894 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2376. Min Act: -0.0001

Data Index: 1229775 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1439949 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1388089 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1369614 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1591652 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2107. Min Act: -0.0001

Data Index: 770837 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.1967. Min Act: -0.0001

Data Index: 889669 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2183. Min Act: -0.0001

Data Index: 1279691 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1395760 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1628910 (Python Code)

Max Activating Token Index: 932

Text #16

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1596388 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1364987 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.1946. Min Act: -0.0001

Data Index: 1585431 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 0.3025. Min Range: -0.3025

Max Act: 0.1810. Min Act: -0.0001

Data Index: 1532401 (Python Code)

Max Activating Token Index: 544