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

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

Neuron 6070 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2512. Min Range: -1.2512

Max Act: 1.2512. Min Act: -0.0000

Data Index: 840125 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.2512. Min Range: -1.2512

Max Act: 1.1709. Min Act: -0.0000

Data Index: 517755 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 1.2512. Min Range: -1.2512

Max Act: 1.1238. Min Act: -0.0000

Data Index: 216019 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.2512. Min Range: -1.2512

Max Act: 1.0703. Min Act: 0.0000

Data Index: 509894 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.2512. Min Range: -1.2512

Max Act: 1.0163. Min Act: -0.0000

Data Index: 619169 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.9308. Min Act: -0.0000

Data Index: 788950 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1226562 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8622. Min Act: -0.0000

Data Index: 835127 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8884. Min Act: 0.0001

Data Index: 1223921 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8867. Min Act: -0.0000

Data Index: 30585 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8381. Min Act: -0.0000

Data Index: 913152 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8403. Min Act: -0.0000

Data Index: 298914 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8786. Min Act: -0.0000

Data Index: 198850 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1584036 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.7926. Min Act: -0.0000

Data Index: 227315 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1013957 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1316869 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1260106 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.7351. Min Act: 0.0000

Data Index: 269421 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 1.2512. Min Range: -1.2512

Max Act: 0.7744. Min Act: -0.0000

Data Index: 834813 (C4 (Web Text))

Max Activating Token Index: 745