Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.6774. Min Act: -0.0001

Data Index: 729144 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.6582. Min Act: -0.0001

Data Index: 585548 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.6345. Min Act: -0.0001

Data Index: 356890 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5390. Min Act: -0.0001

Data Index: 796819 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5304. Min Act: -0.0001

Data Index: 1353924 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5445. Min Act: -0.0001

Data Index: 452477 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5069. Min Act: -0.0001

Data Index: 128542 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5491. Min Act: -0.0001

Data Index: 669440 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5034. Min Act: -0.0001

Data Index: 1298827 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1530527 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5158. Min Act: -0.0001

Data Index: 824992 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4992. Min Act: -0.0001

Data Index: 1600211 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4586. Min Act: -0.0001

Data Index: 36947 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4847. Min Act: -0.0001

Data Index: 38934 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4722. Min Act: -0.0001

Data Index: 1170149 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4862. Min Act: -0.0001

Data Index: 808565 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4597. Min Act: -0.0001

Data Index: 519583 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.5088. Min Act: -0.0001

Data Index: 939053 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4788. Min Act: -0.0001

Data Index: 1007846 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.6774. Min Range: -0.6774

Max Act: 0.4849. Min Act: -0.0000

Data Index: 154828 (C4 (Web Text))

Max Activating Token Index: 354