Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1636 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.4192. Min Act: -0.0003

Data Index: 1482291 (Python Code)

Max Activating Token Index: 312

Text #1

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.4192. Min Act: -0.0003

Data Index: 1483568 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.4188. Min Act: -0.0004

Data Index: 1512636 (Python Code)

Max Activating Token Index: 642

Text #3

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.4095. Min Act: -0.0003

Data Index: 1442617 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3995. Min Act: -0.0003

Data Index: 1532000 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3830. Min Act: -0.0003

Data Index: 1372033 (Python Code)

Max Activating Token Index: 929

Text #6

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3809. Min Act: -0.0003

Data Index: 1524739 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3805. Min Act: -0.0003

Data Index: 1652071 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3709. Min Act: -0.0003

Data Index: 1394787 (Python Code)

Max Activating Token Index: 802

Text #9

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3693. Min Act: -0.0003

Data Index: 1430221 (Python Code)

Max Activating Token Index: 542

Text #10

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3702. Min Act: -0.0003

Data Index: 1431549 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3682. Min Act: -0.0003

Data Index: 1389269 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3986. Min Act: -0.0003

Data Index: 1525527 (Python Code)

Max Activating Token Index: 723

Text #13

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3534. Min Act: -0.0003

Data Index: 1502205 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3548. Min Act: -0.0003

Data Index: 1514161 (Python Code)

Max Activating Token Index: 95

Text #15

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3577. Min Act: -0.0004

Data Index: 1395310 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3601. Min Act: -0.0003

Data Index: 1492401 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3197. Min Act: -0.0003

Data Index: 1523565 (Python Code)

Max Activating Token Index: 320

Text #18

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3487. Min Act: -0.0003

Data Index: 1385427 (Python Code)

Max Activating Token Index: 993

Text #19

Max Range: 0.4192. Min Range: -0.4192

Max Act: 0.3406. Min Act: -0.0003

Data Index: 1608755 (Python Code)

Max Activating Token Index: 849