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

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

Neuron 1166 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1152709 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.7398. Min Act: -0.0000

Data Index: 553988 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.6259. Min Act: -0.0000

Data Index: 146701 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5737. Min Act: -0.0000

Data Index: 486857 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5907. Min Act: -0.0000

Data Index: 60988 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1187186 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.4750. Min Act: -0.0000

Data Index: 665138 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.4488. Min Act: -0.0000

Data Index: 31073 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3804. Min Act: -0.0000

Data Index: 425718 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3925. Min Act: -0.0000

Data Index: 2166 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3827. Min Act: -0.0000

Data Index: 589568 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1064669 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3618. Min Act: -0.0000

Data Index: 645387 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3324. Min Act: -0.0000

Data Index: 850765 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1166907 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3187. Min Act: -0.0000

Data Index: 109801 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.3070. Min Act: -0.0000

Data Index: 541263 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1549504 (Python Code)

Max Activating Token Index: 347

Text #18

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1460408 (Python Code)

Max Activating Token Index: 98

Text #19

Max Range: 0.7917. Min Range: -0.7917

Max Act: 0.2581. Min Act: -0.0000

Data Index: 752254 (C4 (Web Text))

Max Activating Token Index: 999