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

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

Neuron 1152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1474437 (Python Code)

Max Activating Token Index: 781

Text #1

Max Range: 2.4674. Min Range: -2.4674

Max Act: 2.0818. Min Act: -0.0001

Data Index: 1311675 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.8923. Min Act: -0.0000

Data Index: 1021829 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.7301. Min Act: -0.0000

Data Index: 184705 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1187030 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.6930. Min Act: -0.0000

Data Index: 1598643 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.6709. Min Act: -0.0000

Data Index: 1090274 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.6495. Min Act: -0.0000

Data Index: 1612381 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.6420. Min Act: -0.0001

Data Index: 520017 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.6281. Min Act: -0.0000

Data Index: 124731 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.5438. Min Act: -0.0000

Data Index: 619245 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.4925. Min Act: -0.0000

Data Index: 906074 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.6404. Min Act: -0.0000

Data Index: 322027 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.4613. Min Act: -0.0000

Data Index: 181210 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.6168. Min Act: -0.0000

Data Index: 599327 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.2100. Min Act: -0.0000

Data Index: 856816 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.5142. Min Act: -0.0000

Data Index: 992780 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.4729. Min Act: -0.0000

Data Index: 256661 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.3553. Min Act: -0.0000

Data Index: 402277 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 2.4674. Min Range: -2.4674

Max Act: 1.4373. Min Act: -0.0001

Data Index: 749878 (C4 (Web Text))

Max Activating Token Index: 187