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

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

Neuron 4095 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1155159 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.3008. Min Act: -0.0000

Data Index: 603537 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2993. Min Act: 0.0000

Data Index: 1425789 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2992. Min Act: -0.0000

Data Index: 989004 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2798. Min Act: -0.0000

Data Index: 109655 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2771. Min Act: -0.0000

Data Index: 555404 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2537. Min Act: 0.0000

Data Index: 1605600 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1526715 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1180585 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2701. Min Act: -0.0000

Data Index: 432303 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2514. Min Act: 0.0000

Data Index: 1459786 (Python Code)

Max Activating Token Index: 949

Text #11

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1472125 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2492. Min Act: 0.0002

Data Index: 1635694 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1320508 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2358. Min Act: -0.0001

Data Index: 1368522 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2321. Min Act: 0.0001

Data Index: 595655 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2231. Min Act: -0.0000

Data Index: 250886 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2244. Min Act: 0.0001

Data Index: 1633364 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 0.3763. Min Range: -0.3763

Max Act: 0.2328. Min Act: 0.0000

Data Index: 1543691 (Python Code)

Max Activating Token Index: 567