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

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

Neuron 1882 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.4067. Min Act: -0.0000

Data Index: 1451394 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.3542. Min Act: -0.0000

Data Index: 1577598 (Python Code)

Max Activating Token Index: 338

Text #2

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.4458. Min Act: -0.0000

Data Index: 1451416 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.0263. Min Act: -0.0001

Data Index: 1469249 (Python Code)

Max Activating Token Index: 905

Text #4

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.3362. Min Act: -0.0000

Data Index: 1524069 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.9658. Min Act: -0.0000

Data Index: 1633173 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.1262. Min Act: -0.0000

Data Index: 1456642 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.1335. Min Act: -0.0000

Data Index: 1468104 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.1161. Min Act: -0.0000

Data Index: 1444829 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.0912. Min Act: -0.0000

Data Index: 1504104 (Python Code)

Max Activating Token Index: 58

Text #10

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.0533. Min Act: -0.0000

Data Index: 1461605 (Python Code)

Max Activating Token Index: 514

Text #11

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.8738. Min Act: -0.0001

Data Index: 1465512 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.9815. Min Act: -0.0000

Data Index: 1505986 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.8246. Min Act: -0.0000

Data Index: 1427734 (Python Code)

Max Activating Token Index: 535

Text #14

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.8254. Min Act: -0.0000

Data Index: 1485137 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.8164. Min Act: -0.0000

Data Index: 1548623 (Python Code)

Max Activating Token Index: 119

Text #16

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.9699. Min Act: -0.0000

Data Index: 1450738 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.9412. Min Act: -0.0000

Data Index: 1456588 (Python Code)

Max Activating Token Index: 405

Text #18

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.7648. Min Act: -0.0000

Data Index: 1609890 (Python Code)

Max Activating Token Index: 178

Text #19

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.9360. Min Act: -0.0000

Data Index: 1414283 (Python Code)

Max Activating Token Index: 292