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

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

Neuron 4715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0000

Data Index: 943882 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0892. Min Act: -0.0000

Data Index: 467367 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0895. Min Act: -0.0000

Data Index: 304053 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0837. Min Act: -0.0000

Data Index: 835190 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0696. Min Act: -0.0000

Data Index: 878222 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1324348 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0802. Min Act: -0.0000

Data Index: 1361259 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0743. Min Act: -0.0000

Data Index: 416493 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0797. Min Act: -0.0000

Data Index: 12502 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0784. Min Act: -0.0000

Data Index: 487331 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1163336 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1475748 (Python Code)

Max Activating Token Index: 844

Text #12

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0757. Min Act: -0.0000

Data Index: 475663 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1586520 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1112507 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0750. Min Act: -0.0000

Data Index: 891526 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1086334 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0741. Min Act: -0.0000

Data Index: 674718 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0735. Min Act: -0.0000

Data Index: 475960 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0761. Min Act: -0.0000

Data Index: 151071 (C4 (Web Text))

Max Activating Token Index: 617