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

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

Neuron 5695 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0023. Min Range: -2.0023

Max Act: 2.0023. Min Act: -0.0000

Data Index: 847581 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.8477. Min Act: -0.0000

Data Index: 53170 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.8523. Min Act: -0.0000

Data Index: 793024 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.7613. Min Act: -0.0000

Data Index: 893316 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.8130. Min Act: -0.0000

Data Index: 407165 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.7732. Min Act: -0.0000

Data Index: 699051 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.7595. Min Act: -0.0000

Data Index: 238107 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.6502. Min Act: -0.0000

Data Index: 266830 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.5653. Min Act: -0.0000

Data Index: 371693 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.6090. Min Act: -0.0000

Data Index: 986955 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.5140. Min Act: -0.0000

Data Index: 962352 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.5790. Min Act: -0.0000

Data Index: 60625 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.4866. Min Act: -0.0000

Data Index: 44257 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1239755 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.3926. Min Act: -0.0000

Data Index: 871881 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.4688. Min Act: -0.0000

Data Index: 308861 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.3858. Min Act: -0.0000

Data Index: 523813 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.2939. Min Act: -0.0000

Data Index: 246180 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.3517. Min Act: -0.0000

Data Index: 684136 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 2.0023. Min Range: -2.0023

Max Act: 1.3045. Min Act: -0.0000

Data Index: 278440 (C4 (Web Text))

Max Activating Token Index: 990