Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 804 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 14.1688. Min Range: -14.1688

Max Act: 14.1688. Min Act: -0.0001

Data Index: 527954 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 14.1688. Min Range: -14.1688

Max Act: 14.1344. Min Act: -0.0001

Data Index: 48291 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.5915. Min Act: -0.0001

Data Index: 488170 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.0913. Min Act: -0.0001

Data Index: 778979 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.3619. Min Act: -0.0001

Data Index: 1139745 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.1988. Min Act: -0.0001

Data Index: 201999 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.4128. Min Act: -0.0001

Data Index: 1146991 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.2063. Min Act: -0.0001

Data Index: 1164330 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.0968. Min Act: -0.0001

Data Index: 20655 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.1512. Min Act: -0.0001

Data Index: 799615 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.2520. Min Act: -0.0001

Data Index: 248789 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.9673. Min Act: -0.0001

Data Index: 40823 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.6632. Min Act: -0.0001

Data Index: 1088589 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.6005. Min Act: -0.0001

Data Index: 148548 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.7807. Min Act: -0.0001

Data Index: 1260704 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 14.1688. Min Range: -14.1688

Max Act: 13.4156. Min Act: -0.0001

Data Index: 930920 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.7847. Min Act: -0.0001

Data Index: 636781 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.7012. Min Act: -0.0001

Data Index: 1151867 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.2581. Min Act: -0.0001

Data Index: 466531 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 14.1688. Min Range: -14.1688

Max Act: 12.6327. Min Act: -0.0001

Data Index: 1146806 (C4 (Web Text))

Max Activating Token Index: 42