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

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

Neuron 515 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.6289. Min Act: -0.0001

Data Index: 1505025 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1447109 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.5433. Min Act: -0.0000

Data Index: 495883 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.4139. Min Act: -0.0000

Data Index: 470010 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.5848. Min Act: -0.0000

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.4091. Min Act: -0.0001

Data Index: 1610698 (Python Code)

Max Activating Token Index: 1016

Text #6

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.3818. Min Act: -0.0000

Data Index: 442811 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.3338. Min Act: -0.0000

Data Index: 681697 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1457983 (Python Code)

Max Activating Token Index: 478

Text #9

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2694. Min Act: -0.0001

Data Index: 1485089 (Python Code)

Max Activating Token Index: 589

Text #10

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1461325 (Python Code)

Max Activating Token Index: 856

Text #11

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2275. Min Act: -0.0000

Data Index: 131884 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1506518 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1210099 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2345. Min Act: -0.0000

Data Index: 930788 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.3043. Min Act: -0.0001

Data Index: 1444718 (Python Code)

Max Activating Token Index: 131

Text #16

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1633606 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.3596. Min Act: -0.0001

Data Index: 541029 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.2674. Min Act: -0.0001

Data Index: 1638929 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 1.6319. Min Range: -1.6319

Max Act: 1.0133. Min Act: -0.0000

Data Index: 156564 (C4 (Web Text))

Max Activating Token Index: 822