Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1915 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.7468. Min Act: -0.0003

Data Index: 1420574 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6949. Min Act: -0.0003

Data Index: 1372266 (Python Code)

Max Activating Token Index: 641

Text #2

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6542. Min Act: -0.0003

Data Index: 1651491 (Python Code)

Max Activating Token Index: 129

Text #3

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5895. Min Act: -0.0003

Data Index: 1619117 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5722. Min Act: -0.0004

Data Index: 1467593 (Python Code)

Max Activating Token Index: 672

Text #5

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5980. Min Act: -0.0003

Data Index: 1445689 (Python Code)

Max Activating Token Index: 100

Text #6

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6154. Min Act: -0.0003

Data Index: 1594834 (Python Code)

Max Activating Token Index: 545

Text #7

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5937. Min Act: -0.0003

Data Index: 1551426 (Python Code)

Max Activating Token Index: 374

Text #8

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6115. Min Act: -0.0003

Data Index: 1420781 (Python Code)

Max Activating Token Index: 623

Text #9

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6020. Min Act: -0.0003

Data Index: 1368534 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6003. Min Act: -0.0003

Data Index: 1429372 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5878. Min Act: -0.0003

Data Index: 1435037 (Python Code)

Max Activating Token Index: 347

Text #12

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5537. Min Act: -0.0003

Data Index: 1372758 (Python Code)

Max Activating Token Index: 565

Text #13

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6035. Min Act: -0.0003

Data Index: 1405507 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5661. Min Act: -0.0003

Data Index: 1471640 (Python Code)

Max Activating Token Index: 370

Text #15

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.6012. Min Act: -0.0003

Data Index: 1523953 (Python Code)

Max Activating Token Index: 190

Text #16

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5466. Min Act: -0.0003

Data Index: 1481090 (Python Code)

Max Activating Token Index: 89

Text #17

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5628. Min Act: -0.0003

Data Index: 1450729 (Python Code)

Max Activating Token Index: 389

Text #18

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5775. Min Act: -0.0003

Data Index: 1466159 (Python Code)

Max Activating Token Index: 362

Text #19

Max Range: 0.7468. Min Range: -0.7468

Max Act: 0.5594. Min Act: -0.0003

Data Index: 1540491 (Python Code)

Max Activating Token Index: 809