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

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

Neuron 5970 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1142722 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1132917 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.6139. Min Act: 0.0000

Data Index: 994389 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5476. Min Act: -0.0000

Data Index: 530400 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5780. Min Act: -0.0000

Data Index: 285428 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5390. Min Act: 0.0000

Data Index: 375751 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1225774 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5496. Min Act: 0.0000

Data Index: 1105943 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1148702 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5081. Min Act: 0.0000

Data Index: 234518 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5410. Min Act: -0.0000

Data Index: 819652 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5748. Min Act: -0.0000

Data Index: 188900 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5436. Min Act: -0.0000

Data Index: 213096 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1271619 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4766. Min Act: -0.0000

Data Index: 207568 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5010. Min Act: -0.0000

Data Index: 448021 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4751. Min Act: -0.0000

Data Index: 513062 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1109582 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4994. Min Act: -0.0000

Data Index: 259386 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1066687 (C4 (Web Text))

Max Activating Token Index: 406