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

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

Neuron 5456 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: 1.8140. Min Range: -1.8140

Max Act: 1.8140. Min Act: -0.0000

Data Index: 766481 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.4015. Min Act: -0.0000

Data Index: 527709 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.2469. Min Act: -0.0000

Data Index: 37957 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.2036. Min Act: -0.0000

Data Index: 430236 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.1943. Min Act: -0.0000

Data Index: 407144 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.0812. Min Act: -0.0000

Data Index: 534052 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1251034 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.0730. Min Act: -0.0000

Data Index: 878633 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.0074. Min Act: -0.0000

Data Index: 915028 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1355146 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1150728 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.0584. Min Act: -0.0000

Data Index: 741117 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 1.8140. Min Range: -1.8140

Max Act: 1.0466. Min Act: -0.0000

Data Index: 441786 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1262598 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.9739. Min Act: -0.0000

Data Index: 217985 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.9525. Min Act: -0.0000

Data Index: 350348 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1136449 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.9473. Min Act: -0.0000

Data Index: 55553 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.9237. Min Act: -0.0000

Data Index: 63893 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 1.8140. Min Range: -1.8140

Max Act: 0.8460. Min Act: 0.0000

Data Index: 1026136 (C4 (Web Text))

Max Activating Token Index: 204