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

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

Neuron 3473 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: 3.0216. Min Range: -3.0216

Max Act: 2.9354. Min Act: -0.0000

Data Index: 787146 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.4109. Min Act: -0.0000

Data Index: 719678 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.0216. Min Range: -3.0216

Max Act: 3.0216. Min Act: -0.0000

Data Index: 1051976 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.5108. Min Act: -0.0000

Data Index: 320185 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.4175. Min Act: -0.0001

Data Index: 238893 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.4883. Min Act: -0.0000

Data Index: 17146 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.5332. Min Act: -0.0000

Data Index: 1222599 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.5049. Min Act: -0.0000

Data Index: 336560 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.5197. Min Act: -0.0000

Data Index: 976081 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.3996. Min Act: -0.0000

Data Index: 922867 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.5150. Min Act: -0.0000

Data Index: 1327597 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.6981. Min Act: -0.0000

Data Index: 1092801 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.2664. Min Act: -0.0000

Data Index: 900267 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.0821. Min Act: -0.0000

Data Index: 120037 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.5846. Min Act: -0.0000

Data Index: 1014108 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.4562. Min Act: -0.0000

Data Index: 121037 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.5590. Min Act: -0.0000

Data Index: 888370 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.1856. Min Act: -0.0000

Data Index: 944366 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.4984. Min Act: -0.0000

Data Index: 261000 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 3.0216. Min Range: -3.0216

Max Act: 2.2685. Min Act: -0.0000

Data Index: 985784 (C4 (Web Text))

Max Activating Token Index: 4