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

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

Neuron 2509 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1470037 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1408799 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7657. Min Act: -0.0000

Data Index: 1549000 (Python Code)

Max Activating Token Index: 224

Text #3

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1454065 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1544284 (Python Code)

Max Activating Token Index: 298

Text #5

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1561891 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7545. Min Act: -0.0000

Data Index: 1421988 (Python Code)

Max Activating Token Index: 564

Text #7

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1569235 (Python Code)

Max Activating Token Index: 168

Text #8

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7978. Min Act: -0.0000

Data Index: 433052 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1554217 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1611992 (Python Code)

Max Activating Token Index: 365

Text #11

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7330. Min Act: -0.0000

Data Index: 403945 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1651236 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1632430 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1645397 (Python Code)

Max Activating Token Index: 109

Text #15

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1480545 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1474928 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1446784 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1418905 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1564859 (Python Code)

Max Activating Token Index: 364