Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1803 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2972. Min Range: -2.2972

Max Act: 2.2972. Min Act: -0.0000

Data Index: 1543412 (Python Code)

Max Activating Token Index: 581

Text #1

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.9822. Min Act: 0.0000

Data Index: 1518536 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 2.2972. Min Range: -2.2972

Max Act: 2.0181. Min Act: 0.0000

Data Index: 1464177 (Python Code)

Max Activating Token Index: 216

Text #3

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8839. Min Act: -0.0000

Data Index: 1371208 (Python Code)

Max Activating Token Index: 577

Text #4

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8377. Min Act: -0.0000

Data Index: 1489910 (Python Code)

Max Activating Token Index: 142

Text #5

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8332. Min Act: -0.0000

Data Index: 1459368 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1415040 (Python Code)

Max Activating Token Index: 566

Text #7

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8083. Min Act: -0.0000

Data Index: 1468112 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7823. Min Act: -0.0001

Data Index: 1641247 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8180. Min Act: 0.0000

Data Index: 1594244 (Python Code)

Max Activating Token Index: 499

Text #10

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7605. Min Act: 0.0000

Data Index: 1607973 (Python Code)

Max Activating Token Index: 438

Text #11

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8094. Min Act: 0.0000

Data Index: 1596795 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7635. Min Act: 0.0000

Data Index: 1438664 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.6978. Min Act: 0.0000

Data Index: 1568486 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7504. Min Act: -0.0000

Data Index: 1392263 (Python Code)

Max Activating Token Index: 416

Text #15

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7485. Min Act: 0.0000

Data Index: 1498096 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7466. Min Act: 0.0000

Data Index: 1506338 (Python Code)

Max Activating Token Index: 855

Text #17

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7931. Min Act: -0.0001

Data Index: 1655680 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1516307 (Python Code)

Max Activating Token Index: 471

Text #19

Max Range: 2.2972. Min Range: -2.2972

Max Act: 1.8978. Min Act: 0.0000

Data Index: 1384847 (Python Code)

Max Activating Token Index: 1003