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

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

Neuron 4502 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1585287 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.9726. Min Act: -0.0000

Data Index: 1510073 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.7762. Min Act: 0.0000

Data Index: 1599741 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.8103. Min Act: -0.0000

Data Index: 1491804 (Python Code)

Max Activating Token Index: 488

Text #4

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1579056 (Python Code)

Max Activating Token Index: 768

Text #5

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5311. Min Act: -0.0000

Data Index: 1435051 (Python Code)

Max Activating Token Index: 667

Text #6

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.7920. Min Act: -0.0000

Data Index: 1586412 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5749. Min Act: 0.0000

Data Index: 1377602 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5819. Min Act: 0.0000

Data Index: 1430224 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5800. Min Act: 0.0000

Data Index: 1381622 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5905. Min Act: -0.0000

Data Index: 1407563 (Python Code)

Max Activating Token Index: 457

Text #11

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.6212. Min Act: -0.0000

Data Index: 1517991 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.6024. Min Act: 0.0000

Data Index: 1484942 (Python Code)

Max Activating Token Index: 60

Text #13

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.6369. Min Act: 0.0000

Data Index: 1452478 (Python Code)

Max Activating Token Index: 327

Text #14

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1528787 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1402586 (Python Code)

Max Activating Token Index: 987

Text #16

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.4384. Min Act: 0.0000

Data Index: 1396055 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5388. Min Act: 0.0000

Data Index: 1493854 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1359907 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.9726. Min Range: -1.9726

Max Act: 1.5314. Min Act: 0.0000

Data Index: 1621316 (Python Code)

Max Activating Token Index: 173