Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3710 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1639694 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1484160 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0669. Min Act: -0.0000

Data Index: 799595 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1246720 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1565391 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0543. Min Act: -0.0000

Data Index: 1593070 (Python Code)

Max Activating Token Index: 446

Text #6

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0538. Min Act: -0.0000

Data Index: 616463 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0490. Min Act: -0.0000

Data Index: 918374 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1618337 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1391395 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0448. Min Act: -0.0000

Data Index: 1548588 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1563890 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1612008 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1432559 (Python Code)

Max Activating Token Index: 692

Text #14

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0481. Min Act: -0.0000

Data Index: 205961 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1560464 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1527029 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1566419 (Python Code)

Max Activating Token Index: 628

Text #18

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1558569 (Python Code)

Max Activating Token Index: 220

Text #19

Max Range: 0.0939. Min Range: -0.0939

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1375255 (Python Code)

Max Activating Token Index: 662