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

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

Neuron 1976 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: 3.3106. Min Range: -3.3106

Max Act: 3.3106. Min Act: -0.0000

Data Index: 292796 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.7690. Min Act: -0.0000

Data Index: 211519 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.8399. Min Act: -0.0000

Data Index: 1399951 (Python Code)

Max Activating Token Index: 159

Text #3

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.7249. Min Act: -0.0000

Data Index: 386287 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.5390. Min Act: -0.0000

Data Index: 1201256 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.4671. Min Act: -0.0000

Data Index: 1458117 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.4722. Min Act: -0.0000

Data Index: 1492436 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1506306 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1386591 (Python Code)

Max Activating Token Index: 213

Text #9

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1350188 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.4375. Min Act: -0.0000

Data Index: 368912 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.5047. Min Act: -0.0000

Data Index: 97354 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.3783. Min Act: -0.0000

Data Index: 149819 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1407693 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1597101 (Python Code)

Max Activating Token Index: 387

Text #15

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.3934. Min Act: -0.0000

Data Index: 415589 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.3776. Min Act: -0.0000

Data Index: 838348 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.3705. Min Act: -0.0000

Data Index: 211130 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.3692. Min Act: -0.0000

Data Index: 85098 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 3.3106. Min Range: -3.3106

Max Act: 1.5387. Min Act: -0.0000

Data Index: 480342 (C4 (Web Text))

Max Activating Token Index: 283