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

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

Neuron 1313 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5026. Min Range: -3.5026

Max Act: 3.5026. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.5026. Min Range: -3.5026

Max Act: 3.2551. Min Act: -0.0000

Data Index: 1067596 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.9819. Min Act: -0.0000

Data Index: 904289 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.9486. Min Act: -0.0001

Data Index: 334694 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 3.5026. Min Range: -3.5026

Max Act: 3.0085. Min Act: -0.0001

Data Index: 962289 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 3.5026. Min Range: -3.5026

Max Act: 3.0746. Min Act: -0.0000

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.8717. Min Act: -0.0000

Data Index: 218049 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.8536. Min Act: -0.0000

Data Index: 319736 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.7868. Min Act: -0.0000

Data Index: 483044 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.7368. Min Act: -0.0000

Data Index: 676755 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.6298. Min Act: -0.0000

Data Index: 1211677 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.5026. Min Range: -3.5026

Max Act: 3.0537. Min Act: -0.0000

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.3216. Min Act: -0.0001

Data Index: 1123099 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.4203. Min Act: -0.0000

Data Index: 1358487 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 3.5026. Min Range: -3.5026

Max Act: 1.9529. Min Act: -0.0000

Data Index: 548265 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.2465. Min Act: -0.0000

Data Index: 467018 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.3939. Min Act: -0.0001

Data Index: 56474 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.2354. Min Act: -0.0001

Data Index: 1226058 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.2301. Min Act: -0.0001

Data Index: 547131 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 3.5026. Min Range: -3.5026

Max Act: 2.3172. Min Act: -0.0001

Data Index: 1252327 (C4 (Web Text))

Max Activating Token Index: 771