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

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

Neuron 503 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: 0.4807. Min Range: -0.4807

Max Act: 0.4807. Min Act: -0.0000

Data Index: 319889 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1286975 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.4215. Min Act: 0.0000

Data Index: 1107376 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3880. Min Act: 0.0000

Data Index: 427646 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3727. Min Act: -0.0000

Data Index: 72511 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3599. Min Act: -0.0000

Data Index: 731400 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1138157 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3699. Min Act: -0.0000

Data Index: 358912 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3532. Min Act: -0.0000

Data Index: 61434 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3637. Min Act: -0.0000

Data Index: 500526 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1231829 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3598. Min Act: -0.0000

Data Index: 828121 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3391. Min Act: 0.0002

Data Index: 539707 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3438. Min Act: -0.0000

Data Index: 997531 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3389. Min Act: -0.0000

Data Index: 111475 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3469. Min Act: -0.0000

Data Index: 452363 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3349. Min Act: -0.0000

Data Index: 175687 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3705. Min Act: -0.0000

Data Index: 807330 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1217283 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.4807. Min Range: -0.4807

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1193311 (C4 (Web Text))

Max Activating Token Index: 611