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

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

Neuron 2562 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.7191. Min Act: -0.0000

Data Index: 1616139 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4048. Min Act: -0.0000

Data Index: 1542751 (Python Code)

Max Activating Token Index: 93

Text #2

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3975. Min Act: -0.0000

Data Index: 1599584 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4533. Min Act: -0.0000

Data Index: 1585284 (Python Code)

Max Activating Token Index: 514

Text #4

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4510. Min Act: 0.0001

Data Index: 1375021 (Python Code)

Max Activating Token Index: 429

Text #5

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4427. Min Act: -0.0000

Data Index: 1512705 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.4266. Min Act: 0.0000

Data Index: 1363669 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.5183. Min Act: -0.0000

Data Index: 1579266 (Python Code)

Max Activating Token Index: 324

Text #8

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.0417. Min Act: -0.0000

Data Index: 1509969 (Python Code)

Max Activating Token Index: 760

Text #9

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.3636. Min Act: -0.0000

Data Index: 1480934 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.0725. Min Act: -0.0000

Data Index: 1431642 (Python Code)

Max Activating Token Index: 197

Text #11

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.1505. Min Act: 0.0001

Data Index: 1440883 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.1472. Min Act: -0.0000

Data Index: 1563125 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.2513. Min Act: -0.0000

Data Index: 1504228 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 2.7191. Min Range: -2.7191

Max Act: 1.9884. Min Act: 0.0000

Data Index: 1598903 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 2.7191. Min Range: -2.7191

Max Act: 2.1919. Min Act: -0.0000

Data Index: 1508506 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 2.7191. Min Range: -2.7191

Max Act: 1.9146. Min Act: 0.0000

Data Index: 1570688 (Python Code)

Max Activating Token Index: 156

Text #17

Max Range: 2.7191. Min Range: -2.7191

Max Act: 1.9802. Min Act: -0.0000

Data Index: 1644964 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 2.7191. Min Range: -2.7191

Max Act: 1.9175. Min Act: 0.0001

Data Index: 1490334 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 2.7191. Min Range: -2.7191

Max Act: 1.9934. Min Act: 0.0000

Data Index: 1598305 (Python Code)

Max Activating Token Index: 710