Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1446 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5775. Min Act: -0.0001

Data Index: 313927 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5520. Min Act: -0.0001

Data Index: 512275 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5770. Min Act: -0.0001

Data Index: 147728 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5488. Min Act: -0.0001

Data Index: 240834 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5347. Min Act: -0.0001

Data Index: 1097151 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5006. Min Act: -0.0001

Data Index: 62455 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4944. Min Act: -0.0001

Data Index: 838268 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5204. Min Act: -0.0001

Data Index: 515246 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5144. Min Act: -0.0001

Data Index: 524892 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5152. Min Act: -0.0001

Data Index: 923818 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4926. Min Act: -0.0001

Data Index: 201534 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4798. Min Act: -0.0001

Data Index: 645159 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4800. Min Act: -0.0001

Data Index: 621169 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4773. Min Act: -0.0001

Data Index: 1313935 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4858. Min Act: -0.0001

Data Index: 813477 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4847. Min Act: -0.0001

Data Index: 1200859 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4697. Min Act: -0.0001

Data Index: 35869 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4860. Min Act: -0.0001

Data Index: 100544 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.5000. Min Act: -0.0001

Data Index: 1229761 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.5775. Min Range: -0.5775

Max Act: 0.4871. Min Act: -0.0001

Data Index: 184305 (C4 (Web Text))

Max Activating Token Index: 237