Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3894 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1301435 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2483. Min Act: -0.0000

Data Index: 867702 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2517. Min Act: -0.0000

Data Index: 908414 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1243101 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2281. Min Act: -0.0001

Data Index: 276504 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2301. Min Act: -0.0001

Data Index: 68544 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2243. Min Act: -0.0001

Data Index: 318147 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2282. Min Act: -0.0000

Data Index: 756392 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2279. Min Act: -0.0000

Data Index: 383027 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1001554 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2190. Min Act: -0.0001

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2141. Min Act: -0.0000

Data Index: 57937 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2217. Min Act: -0.0000

Data Index: 620924 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1338633 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1320550 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2105. Min Act: -0.0000

Data Index: 992767 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2073. Min Act: -0.0001

Data Index: 796897 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2195. Min Act: -0.0000

Data Index: 799116 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1122557 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.2790. Min Range: -0.2790

Max Act: 0.2010. Min Act: -0.0000

Data Index: 443526 (C4 (Web Text))

Max Activating Token Index: 957