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

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

Neuron 2177 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: 1.6957. Min Range: -1.6957

Max Act: 1.6957. Min Act: -0.0000

Data Index: 1656647 (Python Code)

Max Activating Token Index: 602

Text #1

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1449686 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.5719. Min Act: -0.0000

Data Index: 1508500 (Python Code)

Max Activating Token Index: 480

Text #3

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.5544. Min Act: -0.0000

Data Index: 1399026 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1388739 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1360608 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1471363 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1616731 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.2775. Min Act: -0.0000

Data Index: 1572869 (Python Code)

Max Activating Token Index: 860

Text #9

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.4598. Min Act: -0.0000

Data Index: 1543780 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1611128 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.2661. Min Act: -0.0000

Data Index: 1447575 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3361. Min Act: -0.0000

Data Index: 1445672 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1540104 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1549611 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3231. Min Act: -0.0000

Data Index: 1425792 (Python Code)

Max Activating Token Index: 510

Text #16

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1595411 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1624053 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.2818. Min Act: -0.0000

Data Index: 1543986 (Python Code)

Max Activating Token Index: 164

Text #19

Max Range: 1.6957. Min Range: -1.6957

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1465469 (Python Code)

Max Activating Token Index: 539