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

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

Neuron 5315 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1408. Min Act: -0.0000

Data Index: 668920 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1368. Min Act: -0.0000

Data Index: 453422 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1320. Min Act: -0.0000

Data Index: 908415 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1109. Min Act: -0.0000

Data Index: 84512 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1340. Min Act: -0.0000

Data Index: 611053 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1149. Min Act: -0.0000

Data Index: 691379 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1006. Min Act: -0.0000

Data Index: 555259 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1016. Min Act: -0.0000

Data Index: 545348 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1105. Min Act: -0.0001

Data Index: 978359 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1544025 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1106. Min Act: -0.0000

Data Index: 737723 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0906. Min Act: -0.0000

Data Index: 180549 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0973. Min Act: -0.0000

Data Index: 302822 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0978. Min Act: -0.0000

Data Index: 351115 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1455160 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0946. Min Act: -0.0000

Data Index: 925452 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0997. Min Act: -0.0000

Data Index: 182118 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1154969 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1055. Min Act: -0.0000

Data Index: 751376 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1297195 (C4 (Web Text))

Max Activating Token Index: 264