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

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

Neuron 3950 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.8840. Min Act: -0.0000

Data Index: 1494508 (Python Code)

Max Activating Token Index: 266

Text #1

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1540458 (Python Code)

Max Activating Token Index: 608

Text #2

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.8697. Min Act: -0.0000

Data Index: 1394922 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.8313. Min Act: -0.0000

Data Index: 1602754 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.7686. Min Act: -0.0000

Data Index: 1640217 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.7296. Min Act: -0.0000

Data Index: 1399184 (Python Code)

Max Activating Token Index: 441

Text #6

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1464649 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.6517. Min Act: -0.0000

Data Index: 1557309 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1395844 (Python Code)

Max Activating Token Index: 355

Text #9

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.5611. Min Act: -0.0000

Data Index: 1505622 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.6636. Min Act: -0.0000

Data Index: 1464107 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1419712 (Python Code)

Max Activating Token Index: 197

Text #12

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.4081. Min Act: -0.0000

Data Index: 1650403 (Python Code)

Max Activating Token Index: 302

Text #13

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1644862 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.5536. Min Act: -0.0000

Data Index: 1636802 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.4656. Min Act: -0.0000

Data Index: 1647960 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.5463. Min Act: -0.0000

Data Index: 1467055 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1547574 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.5371. Min Act: -0.0000

Data Index: 1473417 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 1.9954. Min Range: -1.9954

Max Act: 1.5748. Min Act: -0.0000

Data Index: 1646935 (Python Code)

Max Activating Token Index: 675