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

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

Neuron 210 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0061. Min Act: -0.0003

Data Index: 496401 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0060. Min Act: -0.0003

Data Index: 738612 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0056. Min Act: -0.0004

Data Index: 1272371 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0056. Min Act: -0.0003

Data Index: 341281 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1225455 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0054. Min Act: -0.0003

Data Index: 294268 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0054. Min Act: -0.0004

Data Index: 1303401 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0003

Data Index: 380010 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0054. Min Act: -0.0003

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0003

Data Index: 880266 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1268786 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0003

Data Index: 794976 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0003

Data Index: 281750 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0053. Min Act: -0.0004

Data Index: 1123645 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0003

Data Index: 419958 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0004

Data Index: 946417 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0004

Data Index: 491429 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0004

Data Index: 812359 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0003

Data Index: 4935 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0052. Min Act: -0.0003

Data Index: 1409043 (Python Code)

Max Activating Token Index: 958