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

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

Neuron 5449 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.3239. Min Act: -0.0000

Data Index: 233933 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.1735. Min Act: -0.0000

Data Index: 1352364 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.1416. Min Act: -0.0000

Data Index: 693854 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.1256. Min Act: -0.0000

Data Index: 1359276 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.0195. Min Act: -0.0000

Data Index: 1287363 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.2043. Min Act: -0.0000

Data Index: 972500 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.1064. Min Act: -0.0000

Data Index: 1015627 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.9581. Min Act: -0.0000

Data Index: 1104110 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.9909. Min Act: -0.0000

Data Index: 1640861 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.0758. Min Act: -0.0000

Data Index: 1108368 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.0508. Min Act: -0.0000

Data Index: 282553 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.0469. Min Act: -0.0000

Data Index: 110693 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 2.3239. Min Range: -2.3239

Max Act: 2.0224. Min Act: -0.0000

Data Index: 63959 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.9858. Min Act: -0.0000

Data Index: 763014 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.9030. Min Act: -0.0000

Data Index: 334160 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.8892. Min Act: -0.0000

Data Index: 135493 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.9011. Min Act: -0.0000

Data Index: 1152175 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.7931. Min Act: -0.0000

Data Index: 643115 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.8704. Min Act: -0.0000

Data Index: 393738 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 2.3239. Min Range: -2.3239

Max Act: 1.7794. Min Act: -0.0000

Data Index: 983072 (C4 (Web Text))

Max Activating Token Index: 266