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

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

Neuron 231 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.9308. Min Act: -0.0000

Data Index: 254496 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7329. Min Act: -0.0000

Data Index: 81266 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7576. Min Act: -0.0000

Data Index: 606651 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6534. Min Act: -0.0000

Data Index: 520275 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6515. Min Act: -0.0000

Data Index: 396970 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6863. Min Act: -0.0000

Data Index: 489624 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1220785 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5148. Min Act: -0.0000

Data Index: 113290 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.5090. Min Act: -0.0000

Data Index: 816477 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4969. Min Act: -0.0000

Data Index: 165795 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4898. Min Act: -0.0000

Data Index: 988961 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4838. Min Act: -0.0000

Data Index: 301114 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4650. Min Act: -0.0000

Data Index: 701690 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4538. Min Act: -0.0000

Data Index: 66127 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1168444 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4373. Min Act: -0.0000

Data Index: 527900 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4609. Min Act: -0.0000

Data Index: 260156 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1398016 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1175574 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1478672 (Python Code)

Max Activating Token Index: 708