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

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

Neuron 233 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: 1.5839. Min Range: -1.5839

Max Act: 1.5839. Min Act: -0.0001

Data Index: 530544 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.5839. Min Range: -1.5839

Max Act: 1.1269. Min Act: -0.0001

Data Index: 123536 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.5839. Min Range: -1.5839

Max Act: 1.1233. Min Act: -0.0001

Data Index: 1345695 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 1.5839. Min Range: -1.5839

Max Act: 1.1829. Min Act: -0.0001

Data Index: 70393 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.5839. Min Range: -1.5839

Max Act: 1.0952. Min Act: -0.0001

Data Index: 622802 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.5839. Min Range: -1.5839

Max Act: 1.0149. Min Act: -0.0001

Data Index: 456582 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1332685 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.9379. Min Act: -0.0001

Data Index: 442804 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.8009. Min Act: -0.0001

Data Index: 609193 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7853. Min Act: -0.0001

Data Index: 1089667 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.6994. Min Act: -0.0001

Data Index: 266478 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7220. Min Act: -0.0001

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7104. Min Act: -0.0001

Data Index: 523640 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7323. Min Act: -0.0001

Data Index: 449543 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7091. Min Act: -0.0001

Data Index: 920477 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7038. Min Act: -0.0001

Data Index: 1118711 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.6600. Min Act: -0.0001

Data Index: 670793 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.8010. Min Act: -0.0001

Data Index: 1252456 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7988. Min Act: -0.0001

Data Index: 277201 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.5839. Min Range: -1.5839

Max Act: 0.7737. Min Act: -0.0001

Data Index: 412242 (C4 (Web Text))

Max Activating Token Index: 918