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

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

Neuron 409 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4616. Min Act: -0.0001

Data Index: 1375150 (Python Code)

Max Activating Token Index: 557

Text #1

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4486. Min Act: -0.0001

Data Index: 1542537 (Python Code)

Max Activating Token Index: 361

Text #2

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1296219 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4327. Min Act: -0.0001

Data Index: 1439956 (Python Code)

Max Activating Token Index: 500

Text #4

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1591796 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4576. Min Act: -0.0001

Data Index: 1376151 (Python Code)

Max Activating Token Index: 229

Text #6

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4411. Min Act: -0.0001

Data Index: 1564367 (Python Code)

Max Activating Token Index: 630

Text #7

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4256. Min Act: -0.0001

Data Index: 1384317 (Python Code)

Max Activating Token Index: 849

Text #8

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4250. Min Act: -0.0001

Data Index: 1499030 (Python Code)

Max Activating Token Index: 492

Text #9

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4051. Min Act: -0.0001

Data Index: 1616677 (Python Code)

Max Activating Token Index: 659

Text #10

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1488186 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4609. Min Act: -0.0001

Data Index: 1520311 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4404. Min Act: -0.0001

Data Index: 1573208 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4450. Min Act: -0.0001

Data Index: 1380012 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4121. Min Act: -0.0001

Data Index: 1470967 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1589821 (Python Code)

Max Activating Token Index: 398

Text #16

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4327. Min Act: -0.0001

Data Index: 982755 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.3413. Min Act: -0.0001

Data Index: 1653208 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4331. Min Act: -0.0001

Data Index: 1546446 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 0.4616. Min Range: -0.4616

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1087089 (C4 (Web Text))

Max Activating Token Index: 848