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

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

Neuron 4485 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5933. Min Act: -0.0000

Data Index: 1653121 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5002. Min Act: -0.0000

Data Index: 1448456 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1515554 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1509220 (Python Code)

Max Activating Token Index: 557

Text #4

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.5136. Min Act: -0.0000

Data Index: 1451529 (Python Code)

Max Activating Token Index: 767

Text #5

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1459190 (Python Code)

Max Activating Token Index: 893

Text #6

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1516410 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2298. Min Act: -0.0000

Data Index: 1389262 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1602608 (Python Code)

Max Activating Token Index: 348

Text #9

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2005. Min Act: 0.0000

Data Index: 1438334 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2754. Min Act: -0.0000

Data Index: 1601545 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1457333 (Python Code)

Max Activating Token Index: 906

Text #12

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1892. Min Act: -0.0000

Data Index: 1443167 (Python Code)

Max Activating Token Index: 295

Text #13

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.2155. Min Act: 0.0000

Data Index: 1530336 (Python Code)

Max Activating Token Index: 903

Text #14

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1525030 (Python Code)

Max Activating Token Index: 215

Text #15

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1496. Min Act: -0.0000

Data Index: 1522463 (Python Code)

Max Activating Token Index: 475

Text #16

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.1017. Min Act: 0.0000

Data Index: 1503098 (Python Code)

Max Activating Token Index: 966

Text #17

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1582275 (Python Code)

Max Activating Token Index: 873

Text #18

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.0815. Min Act: -0.0000

Data Index: 1602980 (Python Code)

Max Activating Token Index: 426

Text #19

Max Range: 1.5933. Min Range: -1.5933

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1514710 (Python Code)

Max Activating Token Index: 468