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

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

Neuron 1065 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.8197. Min Act: -0.0002

Data Index: 1494264 (Python Code)

Max Activating Token Index: 62

Text #1

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7454. Min Act: -0.0002

Data Index: 1535170 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7242. Min Act: -0.0002

Data Index: 1476419 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7310. Min Act: -0.0002

Data Index: 1649562 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7255. Min Act: -0.0002

Data Index: 1450106 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7173. Min Act: -0.0002

Data Index: 1554672 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6933. Min Act: -0.0002

Data Index: 110125 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6884. Min Act: -0.0002

Data Index: 1458536 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6969. Min Act: -0.0002

Data Index: 1529837 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7013. Min Act: -0.0002

Data Index: 924960 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.7012. Min Act: -0.0002

Data Index: 1221975 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6892. Min Act: -0.0002

Data Index: 1593205 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6899. Min Act: -0.0002

Data Index: 1613389 (Python Code)

Max Activating Token Index: 723

Text #13

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6883. Min Act: -0.0002

Data Index: 696031 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6798. Min Act: -0.0002

Data Index: 616906 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6687. Min Act: -0.0002

Data Index: 663640 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6768. Min Act: -0.0002

Data Index: 1577430 (Python Code)

Max Activating Token Index: 263

Text #17

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6701. Min Act: -0.0002

Data Index: 461436 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6766. Min Act: -0.0002

Data Index: 821543 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.8197. Min Range: -0.8197

Max Act: 0.6780. Min Act: -0.0002

Data Index: 619313 (C4 (Web Text))

Max Activating Token Index: 35