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

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

Neuron 113 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.3194. Min Act: -0.0000

Data Index: 862419 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.5846. Min Act: -0.0000

Data Index: 17936 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.2373. Min Act: -0.0000

Data Index: 368059 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.2483. Min Act: -0.0000

Data Index: 375371 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.9461. Min Act: -0.0000

Data Index: 959071 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.1127. Min Act: -0.0000

Data Index: 449383 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 2.5846. Min Range: -2.5846

Max Act: 2.0213. Min Act: -0.0000

Data Index: 173560 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.9383. Min Act: -0.0000

Data Index: 1162231 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.9931. Min Act: -0.0000

Data Index: 251468 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.7666. Min Act: -0.0000

Data Index: 1014776 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.9245. Min Act: -0.0000

Data Index: 1157323 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.6923. Min Act: -0.0000

Data Index: 862477 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1254459 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.7902. Min Act: -0.0000

Data Index: 589022 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.7257. Min Act: 0.0000

Data Index: 1213923 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.6531. Min Act: -0.0000

Data Index: 17451 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1057980 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.5479. Min Act: -0.0000

Data Index: 576879 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.5066. Min Act: -0.0000

Data Index: 48026 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 2.5846. Min Range: -2.5846

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1100029 (C4 (Web Text))

Max Activating Token Index: 506