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

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

Neuron 2231 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2586. Min Range: -7.2586

Max Act: 7.2586. Min Act: -0.0000

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.8701. Min Act: -0.0000

Data Index: 2945 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.6189. Min Act: -0.0000

Data Index: 771171 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.6722. Min Act: -0.0001

Data Index: 560362 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.6365. Min Act: -0.0001

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.1707. Min Act: -0.0000

Data Index: 1009294 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.3814. Min Act: -0.0001

Data Index: 976160 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.9330. Min Act: -0.0001

Data Index: 296133 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.1624. Min Act: -0.0001

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.0627. Min Act: -0.0001

Data Index: 63621 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.7616. Min Act: -0.0000

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 7.2586. Min Range: -7.2586

Max Act: 6.0192. Min Act: -0.0001

Data Index: 55836 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.9614. Min Act: -0.0001

Data Index: 227216 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.9207. Min Act: -0.0001

Data Index: 48056 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.6905. Min Act: -0.0001

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.7307. Min Act: -0.0001

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.9561. Min Act: -0.0001

Data Index: 501873 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.7972. Min Act: -0.0001

Data Index: 684922 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.4478. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 7.2586. Min Range: -7.2586

Max Act: 5.5562. Min Act: -0.0001

Data Index: 691900 (C4 (Web Text))

Max Activating Token Index: 78