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

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

Neuron 3076 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.6171. Min Act: -0.0000

Data Index: 1389604 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1604171 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1557002 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1569578 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1580401 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1532069 (Python Code)

Max Activating Token Index: 602

Text #6

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1487133 (Python Code)

Max Activating Token Index: 219

Text #7

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1524400 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1622069 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1575653 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1484346 (Python Code)

Max Activating Token Index: 781

Text #11

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1552253 (Python Code)

Max Activating Token Index: 647

Text #12

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1583965 (Python Code)

Max Activating Token Index: 794

Text #13

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1523050 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1566214 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1570587 (Python Code)

Max Activating Token Index: 593

Text #16

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1546729 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1404739 (Python Code)

Max Activating Token Index: 388

Text #18

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1619975 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 0.6171. Min Range: -0.6171

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1442788 (Python Code)

Max Activating Token Index: 621