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

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

Neuron 2554 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3657. Min Range: -3.3657

Max Act: 3.3657. Min Act: -0.0000

Data Index: 725543 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 3.3657. Min Range: -3.3657

Max Act: 3.2215. Min Act: -0.0000

Data Index: 1135276 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 3.3657. Min Range: -3.3657

Max Act: 3.3115. Min Act: -0.0000

Data Index: 1091551 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.8480. Min Act: -0.0000

Data Index: 1324203 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.6128. Min Act: -0.0000

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.6019. Min Act: -0.0000

Data Index: 28382 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.5445. Min Act: -0.0001

Data Index: 1130760 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.4307. Min Act: -0.0000

Data Index: 518847 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.2197. Min Act: -0.0000

Data Index: 1373804 (Python Code)

Max Activating Token Index: 347

Text #9

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.4055. Min Act: -0.0000

Data Index: 516539 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.1181. Min Act: -0.0000

Data Index: 753064 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.1563. Min Act: -0.0000

Data Index: 908892 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.0338. Min Act: -0.0000

Data Index: 933335 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.0461. Min Act: -0.0000

Data Index: 1590246 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.2310. Min Act: -0.0000

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.1040. Min Act: -0.0000

Data Index: 1332173 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 3.3657. Min Range: -3.3657

Max Act: 1.8962. Min Act: -0.0000

Data Index: 936388 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.1125. Min Act: -0.0000

Data Index: 1587854 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 3.3657. Min Range: -3.3657

Max Act: 1.9714. Min Act: -0.0000

Data Index: 931447 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 3.3657. Min Range: -3.3657

Max Act: 2.0364. Min Act: -0.0000

Data Index: 730890 (C4 (Web Text))

Max Activating Token Index: 315