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

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

Neuron 3796 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: 0.3946. Min Range: -0.3946

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1460412 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1500960 (Python Code)

Max Activating Token Index: 786

Text #2

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1536497 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1522463 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1379094 (Python Code)

Max Activating Token Index: 820

Text #5

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1501692 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1537002 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1523011 (Python Code)

Max Activating Token Index: 835

Text #8

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1387014 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1441798 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1580593 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1475609 (Python Code)

Max Activating Token Index: 1009

Text #12

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1444792 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1493435 (Python Code)

Max Activating Token Index: 716

Text #14

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1489406 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1508067 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2979. Min Act: -0.0000

Data Index: 275998 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1537270 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1378006 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3137. Min Act: -0.0000

Data Index: 1632325 (Python Code)

Max Activating Token Index: 564