Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1849 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.2847. Min Act: -0.0001

Data Index: 741429 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.5220. Min Act: -0.0001

Data Index: 348002 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.3714. Min Act: -0.0001

Data Index: 931104 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 3.5493. Min Range: -3.5493

Max Act: 2.8921. Min Act: -0.0001

Data Index: 1157133 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.5493. Min Act: -0.0001

Data Index: 433259 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.3788. Min Act: -0.0001

Data Index: 1310228 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.2086. Min Act: -0.0001

Data Index: 393600 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.1597. Min Act: -0.0001

Data Index: 934319 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.2729. Min Act: -0.0001

Data Index: 958932 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.1158. Min Act: -0.0001

Data Index: 178298 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.2275. Min Act: -0.0001

Data Index: 835814 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.2113. Min Act: -0.0001

Data Index: 1235685 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.1393. Min Act: -0.0001

Data Index: 693622 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 3.5493. Min Range: -3.5493

Max Act: 2.9703. Min Act: -0.0001

Data Index: 556525 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.0649. Min Act: -0.0001

Data Index: 61714 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 3.5493. Min Range: -3.5493

Max Act: 2.8624. Min Act: -0.0001

Data Index: 886687 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 3.5493. Min Range: -3.5493

Max Act: 2.8235. Min Act: -0.0001

Data Index: 1276341 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 3.5493. Min Range: -3.5493

Max Act: 3.0739. Min Act: -0.0001

Data Index: 810955 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 3.5493. Min Range: -3.5493

Max Act: 2.9525. Min Act: -0.0001

Data Index: 66319 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 3.5493. Min Range: -3.5493

Max Act: 2.7890. Min Act: -0.0001

Data Index: 1005121 (C4 (Web Text))

Max Activating Token Index: 896