Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.6256. Min Act: -0.0001

Data Index: 1049324 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 3.6256. Min Range: -3.6256

Max Act: 3.1167. Min Act: -0.0000

Data Index: 828804 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.3893. Min Act: -0.0001

Data Index: 676928 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.4266. Min Act: -0.0000

Data Index: 175295 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.0592. Min Act: -0.0000

Data Index: 42846 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.1753. Min Act: -0.0000

Data Index: 520119 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.2696. Min Act: -0.0000

Data Index: 759115 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.0179. Min Act: -0.0001

Data Index: 1315442 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.1108. Min Act: -0.0000

Data Index: 781456 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.0015. Min Act: -0.0000

Data Index: 1336488 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.0495. Min Act: -0.0000

Data Index: 970283 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.9259. Min Act: -0.0001

Data Index: 1337038 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 3.6256. Min Range: -3.6256

Max Act: 2.1219. Min Act: -0.0000

Data Index: 977345 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.9020. Min Act: -0.0000

Data Index: 449056 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.7838. Min Act: -0.0000

Data Index: 1113444 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.7439. Min Act: -0.0000

Data Index: 825870 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.7429. Min Act: -0.0001

Data Index: 3774 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.7912. Min Act: -0.0001

Data Index: 467556 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.7327. Min Act: -0.0000

Data Index: 467269 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 3.6256. Min Range: -3.6256

Max Act: 1.6865. Min Act: -0.0001

Data Index: 768392 (C4 (Web Text))

Max Activating Token Index: 161