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

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

Neuron 3399 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: 0.3227. Min Range: -0.3227

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1353586 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2954. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1645916 (Python Code)

Max Activating Token Index: 877

Text #4

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1499694 (Python Code)

Max Activating Token Index: 347

Text #5

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2741. Min Act: -0.0000

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2510. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1534589 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1654361 (Python Code)

Max Activating Token Index: 935

Text #11

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2503. Min Act: -0.0000

Data Index: 670086 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1589709 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1516769 (Python Code)

Max Activating Token Index: 333

Text #14

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2422. Min Act: -0.0000

Data Index: 163452 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1395261 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1610926 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1454713 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1464021 (Python Code)

Max Activating Token Index: 630

Text #19

Max Range: 0.3227. Min Range: -0.3227

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1425519 (Python Code)

Max Activating Token Index: 885