Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 86 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4359. Min Act: -0.0000

Data Index: 693665 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4592. Min Act: -0.0000

Data Index: 118576 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4009. Min Act: -0.0000

Data Index: 547074 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3904. Min Act: -0.0000

Data Index: 730246 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1009880 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3973. Min Act: -0.0000

Data Index: 957420 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.4102. Min Act: -0.0000

Data Index: 532656 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3716. Min Act: -0.0000

Data Index: 156966 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3681. Min Act: -0.0000

Data Index: 948271 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3798. Min Act: -0.0000

Data Index: 377163 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3554. Min Act: -0.0000

Data Index: 396281 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3887. Min Act: -0.0000

Data Index: 376450 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3361. Min Act: -0.0000

Data Index: 510584 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3553. Min Act: -0.0000

Data Index: 232975 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3313. Min Act: -0.0000

Data Index: 132016 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1334471 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3299. Min Act: -0.0000

Data Index: 679353 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1013350 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2986. Min Act: -0.0000

Data Index: 94813 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.4592. Min Range: -0.4592

Max Act: 0.2994. Min Act: -0.0000

Data Index: 964422 (C4 (Web Text))

Max Activating Token Index: 1001