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

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

Neuron 624 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.5157. Min Act: -0.0000

Data Index: 224975 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1652730 (Python Code)

Max Activating Token Index: 201

Text #2

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1312321 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1641180 (Python Code)

Max Activating Token Index: 341

Text #4

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1647149 (Python Code)

Max Activating Token Index: 423

Text #5

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1641122 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1438774 (Python Code)

Max Activating Token Index: 883

Text #7

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1424863 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1614791 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3097. Min Act: -0.0000

Data Index: 748614 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1390600 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1466520 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1041318 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1361612 (Python Code)

Max Activating Token Index: 120

Text #14

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.2945. Min Act: -0.0000

Data Index: 275645 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.2916. Min Act: -0.0000

Data Index: 505731 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.2873. Min Act: -0.0000

Data Index: 1580180 (Python Code)

Max Activating Token Index: 463

Text #17

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1468855 (Python Code)

Max Activating Token Index: 749

Text #18

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.2970. Min Act: -0.0000

Data Index: 1399958 (Python Code)

Max Activating Token Index: 130

Text #19

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1541994 (Python Code)

Max Activating Token Index: 743