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

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

Neuron 4797 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.3761. Min Act: -0.0000

Data Index: 425256 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.8109. Min Act: -0.0001

Data Index: 872834 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 3.3761. Min Range: -3.3761

Max Act: 3.0900. Min Act: -0.0000

Data Index: 1147100 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.8830. Min Act: -0.0000

Data Index: 881142 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.9754. Min Act: -0.0000

Data Index: 9618 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.6840. Min Act: -0.0000

Data Index: 712345 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.6209. Min Act: -0.0001

Data Index: 171293 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.4265. Min Act: -0.0001

Data Index: 864329 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.6638. Min Act: -0.0001

Data Index: 1331626 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.4949. Min Act: -0.0000

Data Index: 586398 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.4847. Min Act: -0.0000

Data Index: 108428 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.4921. Min Act: -0.0000

Data Index: 804358 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.4740. Min Act: -0.0000

Data Index: 244500 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5616. Min Act: -0.0001

Data Index: 277692 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.5483. Min Act: -0.0001

Data Index: 402668 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.2456. Min Act: -0.0001

Data Index: 388914 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.3355. Min Act: -0.0001

Data Index: 303645 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.3492. Min Act: -0.0001

Data Index: 1113382 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.4521. Min Act: -0.0001

Data Index: 1055860 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 3.3761. Min Range: -3.3761

Max Act: 2.3630. Min Act: -0.0000

Data Index: 395572 (C4 (Web Text))

Max Activating Token Index: 763