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

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

Neuron 2125 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1065352 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.5348. Min Act: -0.0000

Data Index: 236917 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1351686 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1038578 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4668. Min Act: -0.0000

Data Index: 104024 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1066020 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4657. Min Act: -0.0000

Data Index: 816876 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1260890 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4834. Min Act: -0.0000

Data Index: 89012 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4671. Min Act: -0.0000

Data Index: 689204 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1239144 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4605. Min Act: -0.0000

Data Index: 121284 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4295. Min Act: -0.0000

Data Index: 362110 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4364. Min Act: -0.0000

Data Index: 574563 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4334. Min Act: -0.0000

Data Index: 875176 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4191. Min Act: -0.0000

Data Index: 830834 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1329762 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1133565 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3798. Min Act: -0.0000

Data Index: 186545 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1274956 (C4 (Web Text))

Max Activating Token Index: 155