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

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

Neuron 1830 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3528. Min Act: -0.0001

Data Index: 472748 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3532. Min Act: -0.0001

Data Index: 846907 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3237. Min Act: -0.0001

Data Index: 166923 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3265. Min Act: -0.0001

Data Index: 702340 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3144. Min Act: -0.0001

Data Index: 907889 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3080. Min Act: -0.0001

Data Index: 334076 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3075. Min Act: -0.0001

Data Index: 614549 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3164. Min Act: -0.0001

Data Index: 140278 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1105139 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2967. Min Act: -0.0000

Data Index: 719677 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2921. Min Act: -0.0001

Data Index: 1242712 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2625. Min Act: -0.0001

Data Index: 214109 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2603. Min Act: -0.0001

Data Index: 257777 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2653. Min Act: -0.0001

Data Index: 756133 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2840. Min Act: -0.0001

Data Index: 630160 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1287451 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2897. Min Act: -0.0001

Data Index: 599191 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2632. Min Act: -0.0001

Data Index: 219213 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2621. Min Act: -0.0001

Data Index: 742742 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2586. Min Act: -0.0000

Data Index: 408131 (C4 (Web Text))

Max Activating Token Index: 672