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

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

Neuron 312 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5486. Min Range: -7.5486

Max Act: 7.5486. Min Act: -0.0000

Data Index: 1193303 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.8121. Min Act: -0.0000

Data Index: 524108 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.1473. Min Act: -0.0000

Data Index: 1191520 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.3855. Min Act: -0.0000

Data Index: 607871 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.4534. Min Act: -0.0000

Data Index: 15720 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.5858. Min Act: -0.0000

Data Index: 546909 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.1324. Min Act: -0.0000

Data Index: 900827 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.1411. Min Act: -0.0000

Data Index: 554964 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.7773. Min Act: -0.0000

Data Index: 554537 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 7.5486. Min Range: -7.5486

Max Act: 4.0690. Min Act: -0.0000

Data Index: 65922 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.7410. Min Act: -0.0000

Data Index: 900510 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.7614. Min Act: -0.0000

Data Index: 870382 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.6294. Min Act: -0.0000

Data Index: 1095822 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.7606. Min Act: -0.0000

Data Index: 664171 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.5720. Min Act: -0.0000

Data Index: 1023986 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.4927. Min Act: -0.0000

Data Index: 635133 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.0210. Min Act: -0.0000

Data Index: 402298 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.4453. Min Act: -0.0000

Data Index: 211510 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.4323. Min Act: -0.0000

Data Index: 1343265 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 7.5486. Min Range: -7.5486

Max Act: 3.2523. Min Act: -0.0000

Data Index: 20019 (C4 (Web Text))

Max Activating Token Index: 187