Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2121 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1238378 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5646. Min Act: -0.0000

Data Index: 245622 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.5320. Min Act: -0.0000

Data Index: 793242 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4894. Min Act: -0.0000

Data Index: 379657 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4783. Min Act: -0.0000

Data Index: 928954 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4304. Min Act: -0.0000

Data Index: 127385 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4350. Min Act: -0.0000

Data Index: 761006 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4184. Min Act: -0.0000

Data Index: 336146 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1235848 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4423. Min Act: -0.0000

Data Index: 158517 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1145800 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1029010 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3863. Min Act: -0.0000

Data Index: 625234 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3872. Min Act: -0.0000

Data Index: 226348 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3918. Min Act: -0.0000

Data Index: 450050 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3739. Min Act: -0.0000

Data Index: 684230 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3544. Min Act: -0.0000

Data Index: 728895 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3570. Min Act: -0.0000

Data Index: 180305 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1156574 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.5646. Min Range: -0.5646

Max Act: 0.3697. Min Act: -0.0000

Data Index: 932411 (C4 (Web Text))

Max Activating Token Index: 957