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

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

Neuron 6006 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.7659. Min Act: -0.0000

Data Index: 625075 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.4976. Min Act: -0.0000

Data Index: 1279794 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.6869. Min Act: -0.0000

Data Index: 143196 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.2162. Min Act: -0.0000

Data Index: 1119618 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.1457. Min Act: -0.0000

Data Index: 316367 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.2677. Min Act: -0.0000

Data Index: 135258 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.0243. Min Act: -0.0000

Data Index: 1312815 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.9430. Min Act: -0.0000

Data Index: 104249 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.8633. Min Act: -0.0000

Data Index: 1070020 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.0363. Min Act: -0.0000

Data Index: 998669 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 4.7659. Min Range: -4.7659

Max Act: 4.0445. Min Act: -0.0000

Data Index: 759897 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.8235. Min Act: -0.0000

Data Index: 722512 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.9481. Min Act: -0.0000

Data Index: 517063 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.6709. Min Act: -0.0000

Data Index: 775108 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.6422. Min Act: -0.0000

Data Index: 790333 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.6497. Min Act: -0.0000

Data Index: 599729 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.5997. Min Act: -0.0000

Data Index: 767334 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.5644. Min Act: -0.0000

Data Index: 1036337 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.7384. Min Act: -0.0000

Data Index: 721149 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 4.7659. Min Range: -4.7659

Max Act: 3.7308. Min Act: -0.0000

Data Index: 210281 (C4 (Web Text))

Max Activating Token Index: 78