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

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

Neuron 1989 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: 3.5065. Min Range: -3.5065

Max Act: 3.2947. Min Act: -0.0000

Data Index: 309982 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 3.5065. Min Range: -3.5065

Max Act: 3.5065. Min Act: -0.0000

Data Index: 347105 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.7161. Min Act: -0.0000

Data Index: 131966 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.9575. Min Act: -0.0000

Data Index: 397100 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.7925. Min Act: -0.0000

Data Index: 1028284 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.7260. Min Act: -0.0000

Data Index: 417410 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.6333. Min Act: -0.0000

Data Index: 1312095 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.6380. Min Act: -0.0000

Data Index: 711526 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.4846. Min Act: -0.0000

Data Index: 725472 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.6229. Min Act: -0.0000

Data Index: 89606 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.5769. Min Act: -0.0000

Data Index: 158828 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.6562. Min Act: -0.0000

Data Index: 264293 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.5063. Min Act: -0.0000

Data Index: 1077885 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.4875. Min Act: -0.0000

Data Index: 889699 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.4029. Min Act: -0.0000

Data Index: 415836 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.2892. Min Act: -0.0000

Data Index: 207820 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.3991. Min Act: -0.0000

Data Index: 119446 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.2775. Min Act: -0.0000

Data Index: 1344625 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.3668. Min Act: -0.0000

Data Index: 563122 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 3.5065. Min Range: -3.5065

Max Act: 2.3368. Min Act: -0.0000

Data Index: 578214 (C4 (Web Text))

Max Activating Token Index: 526