Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4132 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.5926. Min Act: -0.0000

Data Index: 68810 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.4664. Min Act: -0.0000

Data Index: 1332349 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.1416. Min Act: -0.0000

Data Index: 445675 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.3574. Min Act: -0.0000

Data Index: 252622 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.0616. Min Act: -0.0000

Data Index: 420568 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.1549. Min Act: -0.0000

Data Index: 1223910 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.9412. Min Act: -0.0000

Data Index: 474684 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.0039. Min Act: -0.0000

Data Index: 1173869 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.0780. Min Act: -0.0000

Data Index: 48400 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.0093. Min Act: -0.0000

Data Index: 734880 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.9946. Min Act: -0.0000

Data Index: 1135027 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1140018 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.0668. Min Act: -0.0000

Data Index: 1287040 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.9342. Min Act: -0.0000

Data Index: 476008 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.9265. Min Act: -0.0000

Data Index: 1105051 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 2.5926. Min Range: -2.5926

Max Act: 2.0101. Min Act: -0.0000

Data Index: 369715 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.9778. Min Act: -0.0000

Data Index: 974803 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.8817. Min Act: -0.0000

Data Index: 989456 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.8687. Min Act: -0.0000

Data Index: 860350 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 2.5926. Min Range: -2.5926

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1121763 (C4 (Web Text))

Max Activating Token Index: 515