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

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

Neuron 2545 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0870. Min Range: -2.0870

Max Act: 2.0414. Min Act: -0.0000

Data Index: 120119 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.9965. Min Act: -0.0000

Data Index: 29561 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 2.0870. Min Range: -2.0870

Max Act: 2.0870. Min Act: -0.0000

Data Index: 25177 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.9049. Min Act: -0.0000

Data Index: 885545 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.8190. Min Act: -0.0000

Data Index: 1085923 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.8860. Min Act: -0.0000

Data Index: 431695 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.6638. Min Act: -0.0000

Data Index: 997436 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.7022. Min Act: -0.0000

Data Index: 196474 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.7069. Min Act: -0.0000

Data Index: 262923 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.8906. Min Act: -0.0000

Data Index: 55041 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.5997. Min Act: -0.0000

Data Index: 273073 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.7854. Min Act: -0.0000

Data Index: 1310397 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.6008. Min Act: -0.0000

Data Index: 964612 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.6652. Min Act: -0.0000

Data Index: 728694 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.6736. Min Act: -0.0000

Data Index: 404396 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.9278. Min Act: -0.0000

Data Index: 209186 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.6643. Min Act: -0.0000

Data Index: 1106917 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.6089. Min Act: -0.0000

Data Index: 45002 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.7853. Min Act: -0.0000

Data Index: 553739 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 2.0870. Min Range: -2.0870

Max Act: 1.5702. Min Act: -0.0000

Data Index: 1210695 (C4 (Web Text))

Max Activating Token Index: 455