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

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

Neuron 2154 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0683. Min Act: -0.0002

Data Index: 352398 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0637. Min Act: -0.0002

Data Index: 838220 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1335802 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0625. Min Act: -0.0002

Data Index: 446710 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0603. Min Act: -0.0002

Data Index: 23074 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0519. Min Act: -0.0002

Data Index: 954841 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0546. Min Act: -0.0002

Data Index: 76663 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0556. Min Act: -0.0002

Data Index: 326699 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0587. Min Act: -0.0002

Data Index: 790669 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0543. Min Act: -0.0002

Data Index: 945126 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0557. Min Act: -0.0002

Data Index: 801998 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0461. Min Act: -0.0002

Data Index: 27111 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0545. Min Act: -0.0002

Data Index: 371620 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1106733 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1024498 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0550. Min Act: -0.0002

Data Index: 760555 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0506. Min Act: -0.0002

Data Index: 903291 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0489. Min Act: -0.0002

Data Index: 912684 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1252118 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0683. Min Range: -0.0683

Max Act: 0.0543. Min Act: -0.0002

Data Index: 707008 (C4 (Web Text))

Max Activating Token Index: 645