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

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

Neuron 3311 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: 0.7788. Min Range: -0.7788

Max Act: 0.7735. Min Act: -0.0000

Data Index: 578900 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1362586 (Python Code)

Max Activating Token Index: 473

Text #2

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1583906 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.7267. Min Act: -0.0000

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1535210 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1439646 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1637999 (Python Code)

Max Activating Token Index: 580

Text #7

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1360365 (Python Code)

Max Activating Token Index: 288

Text #8

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1512135 (Python Code)

Max Activating Token Index: 859

Text #9

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1530043 (Python Code)

Max Activating Token Index: 560

Text #10

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1473510 (Python Code)

Max Activating Token Index: 649

Text #11

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1094280 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1585234 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1554111 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1505935 (Python Code)

Max Activating Token Index: 713

Text #15

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1414709 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5389. Min Act: -0.0000

Data Index: 885507 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1485146 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.5024. Min Act: 0.0000

Data Index: 1437000 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 0.7788. Min Range: -0.7788

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1606352 (Python Code)

Max Activating Token Index: 307