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

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

Neuron 2156 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9653. Min Act: -0.0000

Data Index: 869103 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.8768. Min Act: -0.0000

Data Index: 426763 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.6070. Min Act: -0.0000

Data Index: 919025 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1186708 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.5262. Min Act: -0.0000

Data Index: 1109013 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1322741 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.4441. Min Act: -0.0000

Data Index: 197372 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1256014 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.0806. Min Act: -0.0000

Data Index: 1118035 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.0050. Min Act: -0.0000

Data Index: 188565 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.1122. Min Act: 0.0000

Data Index: 400994 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.0253. Min Act: -0.0000

Data Index: 257572 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 1.9653. Min Range: -1.9653

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1277875 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.0035. Min Act: -0.0000

Data Index: 870807 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.9653. Min Range: -1.9653

Max Act: 0.9841. Min Act: -0.0000

Data Index: 393438 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 1.9653. Min Range: -1.9653

Max Act: 0.9770. Min Act: -0.0000

Data Index: 74685 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.9653. Min Range: -1.9653

Max Act: 0.9796. Min Act: -0.0000

Data Index: 216553 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.0164. Min Act: -0.0000

Data Index: 82332 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.9653. Min Range: -1.9653

Max Act: 0.9004. Min Act: -0.0000

Data Index: 325110 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 1.9653. Min Range: -1.9653

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1235422 (C4 (Web Text))

Max Activating Token Index: 478