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

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

Neuron 4250 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.6469. Min Act: -0.0000

Data Index: 23748 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 1.6469. Min Range: -1.6469

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1354244 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1276836 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1120060 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1065550 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8671. Min Act: -0.0000

Data Index: 79920 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8569. Min Act: -0.0000

Data Index: 1324108 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8217. Min Act: -0.0000

Data Index: 445112 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1338890 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8231. Min Act: -0.0000

Data Index: 47840 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1137453 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8402. Min Act: -0.0000

Data Index: 709410 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1048737 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8598. Min Act: -0.0000

Data Index: 63140 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8035. Min Act: -0.0000

Data Index: 520952 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1256075 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8017. Min Act: -0.0000

Data Index: 406668 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.8026. Min Act: -0.0000

Data Index: 526388 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.7913. Min Act: -0.0000

Data Index: 103303 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.6469. Min Range: -1.6469

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1043821 (C4 (Web Text))

Max Activating Token Index: 543