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

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

Neuron 4518 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4842. Min Act: -0.0000

Data Index: 448219 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4658. Min Act: -0.0001

Data Index: 398029 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4363. Min Act: -0.0001

Data Index: 482198 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1250765 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4409. Min Act: -0.0001

Data Index: 741292 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3735. Min Act: -0.0001

Data Index: 1109869 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.4020. Min Act: -0.0001

Data Index: 498212 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3740. Min Act: -0.0001

Data Index: 203261 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3995. Min Act: -0.0001

Data Index: 454726 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3813. Min Act: -0.0001

Data Index: 639179 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3809. Min Act: -0.0001

Data Index: 698683 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1117734 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1265523 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1104903 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3260. Min Act: -0.0001

Data Index: 1333990 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3696. Min Act: -0.0001

Data Index: 519332 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3286. Min Act: -0.0001

Data Index: 479229 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3506. Min Act: -0.0001

Data Index: 15385 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3565. Min Act: -0.0000

Data Index: 128589 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.4842. Min Range: -0.4842

Max Act: 0.3393. Min Act: -0.0001

Data Index: 1616154 (Python Code)

Max Activating Token Index: 352