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

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

Neuron 2453 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: 1.2936. Min Range: -1.2936

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1537550 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1404514 (Python Code)

Max Activating Token Index: 885

Text #2

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1050. Min Act: -0.0000

Data Index: 1536587 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1566465 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 1.2936. Min Range: -1.2936

Max Act: 1.2097. Min Act: -0.0000

Data Index: 1424209 (Python Code)

Max Activating Token Index: 611

Text #5

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1567007 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1652329 (Python Code)

Max Activating Token Index: 453

Text #7

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1514438 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1428022 (Python Code)

Max Activating Token Index: 562

Text #9

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1473961 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7092. Min Act: -0.0000

Data Index: 1656338 (Python Code)

Max Activating Token Index: 957

Text #11

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1474066 (Python Code)

Max Activating Token Index: 866

Text #12

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1390071 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1522247 (Python Code)

Max Activating Token Index: 390

Text #14

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1582495 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1466243 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1587368 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1398510 (Python Code)

Max Activating Token Index: 866

Text #18

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1498653 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 1.2936. Min Range: -1.2936

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1562077 (Python Code)

Max Activating Token Index: 733