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

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

Neuron 3171 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: 3.7100. Min Range: -3.7100

Max Act: 3.7100. Min Act: -0.0001

Data Index: 1321434 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.5366. Min Act: -0.0001

Data Index: 836359 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.6078. Min Act: -0.0001

Data Index: 1088761 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.5383. Min Act: -0.0001

Data Index: 641986 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.1725. Min Act: -0.0001

Data Index: 181083 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.3022. Min Act: -0.0001

Data Index: 1351065 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.1522. Min Act: -0.0001

Data Index: 1127163 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.2689. Min Act: -0.0001

Data Index: 259593 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.9202. Min Act: -0.0001

Data Index: 255361 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.9590. Min Act: -0.0001

Data Index: 713420 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.9858. Min Act: -0.0001

Data Index: 839103 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.0016. Min Act: -0.0001

Data Index: 1096950 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.1370. Min Act: -0.0001

Data Index: 1237054 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.7100. Min Range: -3.7100

Max Act: 3.1433. Min Act: -0.0001

Data Index: 444292 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.9790. Min Act: -0.0001

Data Index: 725513 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.7998. Min Act: -0.0001

Data Index: 649652 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.9166. Min Act: -0.0001

Data Index: 1153988 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.8978. Min Act: -0.0001

Data Index: 169361 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.8558. Min Act: -0.0001

Data Index: 583376 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.7100. Min Range: -3.7100

Max Act: 2.7397. Min Act: -0.0001

Data Index: 68618 (C4 (Web Text))

Max Activating Token Index: 114