Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1009 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0006

Data Index: 1412849 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0311. Min Act: -0.0006

Data Index: 1465696 (Python Code)

Max Activating Token Index: 227

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0310. Min Act: -0.0006

Data Index: 1516174 (Python Code)

Max Activating Token Index: 296

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0310. Min Act: -0.0006

Data Index: 1483457 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1565090 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1614559 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0305. Min Act: -0.0006

Data Index: 1509332 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1566306 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0301. Min Act: -0.0006

Data Index: 1646124 (Python Code)

Max Activating Token Index: 435

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1362419 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0298. Min Act: -0.0006

Data Index: 1525382 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1495280 (Python Code)

Max Activating Token Index: 767

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1516762 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1421127 (Python Code)

Max Activating Token Index: 437

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1407111 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1651934 (Python Code)

Max Activating Token Index: 543

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0300. Min Act: -0.0006

Data Index: 1533433 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1491872 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0293. Min Act: -0.0006

Data Index: 1556787 (Python Code)

Max Activating Token Index: 500

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1631845 (Python Code)

Max Activating Token Index: 134