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

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

Neuron 3451 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1371739 (Python Code)

Max Activating Token Index: 973

Text #1

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1445718 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1371104 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1587839 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1409834 (Python Code)

Max Activating Token Index: 286

Text #5

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1495296 (Python Code)

Max Activating Token Index: 57

Text #6

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1492110 (Python Code)

Max Activating Token Index: 844

Text #7

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1481784 (Python Code)

Max Activating Token Index: 590

Text #8

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1656370 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1415089 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1368400 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1384602 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3345. Min Act: -0.0000

Data Index: 1455351 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1597171 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1445063 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3298. Min Act: -0.0000

Data Index: 1560346 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1459014 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1560490 (Python Code)

Max Activating Token Index: 837

Text #18

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1381440 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 0.4956. Min Range: -0.4956

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1557632 (Python Code)

Max Activating Token Index: 847