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

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

Neuron 1558 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: 0.3211. Min Range: -0.3211

Max Act: 0.3211. Min Act: 0.0002

Data Index: 1337589 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2542. Min Act: 0.0001

Data Index: 301364 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1151256 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2466. Min Act: -0.0000

Data Index: 928307 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2212. Min Act: -0.0000

Data Index: 200045 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2158. Min Act: -0.0000

Data Index: 204605 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2039. Min Act: -0.0001

Data Index: 732335 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2087. Min Act: -0.0000

Data Index: 945251 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2106. Min Act: -0.0000

Data Index: 960245 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1950. Min Act: -0.0001

Data Index: 830467 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2009. Min Act: 0.0000

Data Index: 1261107 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1990. Min Act: 0.0000

Data Index: 1077202 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1976. Min Act: -0.0001

Data Index: 768782 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1957. Min Act: -0.0001

Data Index: 125664 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1950. Min Act: -0.0001

Data Index: 973696 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1954. Min Act: 0.0001

Data Index: 258117 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1867. Min Act: -0.0000

Data Index: 362817 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1901. Min Act: -0.0000

Data Index: 896708 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1116576 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.1934. Min Act: 0.0000

Data Index: 170304 (C4 (Web Text))

Max Activating Token Index: 70