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

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

Neuron 1605 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8614. Min Range: -3.8614

Max Act: 3.8614. Min Act: -0.0000

Data Index: 1013748 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 3.8614. Min Range: -3.8614

Max Act: 3.0003. Min Act: -0.0001

Data Index: 355411 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.8591. Min Act: -0.0001

Data Index: 184169 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.8354. Min Act: -0.0000

Data Index: 923513 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.5587. Min Act: -0.0001

Data Index: 1167801 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.9326. Min Act: -0.0001

Data Index: 793888 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.8412. Min Act: -0.0001

Data Index: 588331 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.7680. Min Act: -0.0001

Data Index: 866739 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.6006. Min Act: -0.0000

Data Index: 941801 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.6869. Min Act: -0.0001

Data Index: 671471 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.5649. Min Act: -0.0001

Data Index: 851689 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.5230. Min Act: -0.0001

Data Index: 77289 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.3878. Min Act: -0.0001

Data Index: 381670 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.2742. Min Act: -0.0001

Data Index: 628391 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.2478. Min Act: -0.0001

Data Index: 250316 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.4834. Min Act: -0.0001

Data Index: 372138 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.4889. Min Act: -0.0001

Data Index: 784429 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.4803. Min Act: -0.0001

Data Index: 272060 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.3508. Min Act: -0.0001

Data Index: 674781 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 3.8614. Min Range: -3.8614

Max Act: 2.5927. Min Act: -0.0001

Data Index: 11096 (C4 (Web Text))

Max Activating Token Index: 697