Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 332 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1365069 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0074. Min Act: -0.0006

Data Index: 1416927 (Python Code)

Max Activating Token Index: 750

Text #2

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0070. Min Act: -0.0006

Data Index: 13750 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0072. Min Act: -0.0006

Data Index: 538055 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0070. Min Act: -0.0006

Data Index: 449356 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1045507 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1476798 (Python Code)

Max Activating Token Index: 855

Text #7

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1639897 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1200229 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 250267 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0066. Min Act: -0.0006

Data Index: 276630 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1377008 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1303473 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0064. Min Act: -0.0006

Data Index: 918545 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0062. Min Act: -0.0006

Data Index: 852887 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0063. Min Act: -0.0006

Data Index: 798202 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1367237 (Python Code)

Max Activating Token Index: 321

Text #17

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1053986 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1638094 (Python Code)

Max Activating Token Index: 725

Text #19

Max Range: 0.0074. Min Range: -0.0074

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1308591 (C4 (Web Text))

Max Activating Token Index: 478