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

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

Neuron 3259 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5479. Min Act: -0.0000

Data Index: 705078 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1219581 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5184. Min Act: -0.0000

Data Index: 619186 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1306358 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4511. Min Act: -0.0000

Data Index: 503330 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1070525 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4828. Min Act: -0.0000

Data Index: 63386 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4287. Min Act: -0.0000

Data Index: 967431 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4465. Min Act: -0.0000

Data Index: 634379 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.5255. Min Act: -0.0000

Data Index: 241910 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4701. Min Act: -0.0000

Data Index: 394298 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1024301 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4379. Min Act: -0.0000

Data Index: 515457 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.3938. Min Act: -0.0000

Data Index: 474562 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4328. Min Act: -0.0000

Data Index: 278973 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4713. Min Act: -0.0000

Data Index: 80050 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4113. Min Act: -0.0000

Data Index: 404604 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4272. Min Act: -0.0000

Data Index: 305365 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4889. Min Act: -0.0000

Data Index: 44122 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.5532. Min Range: -0.5532

Max Act: 0.4450. Min Act: -0.0000

Data Index: 643374 (C4 (Web Text))

Max Activating Token Index: 894