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

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

Neuron 3898 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.7699. Min Act: -0.0000

Data Index: 732622 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6943. Min Act: -0.0000

Data Index: 307117 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6957. Min Act: -0.0000

Data Index: 8149 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6988. Min Act: -0.0000

Data Index: 892389 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1294117 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1120986 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1051758 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5229. Min Act: -0.0000

Data Index: 739403 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1138726 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5238. Min Act: -0.0000

Data Index: 922645 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.5197. Min Act: -0.0000

Data Index: 620745 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4668. Min Act: -0.0000

Data Index: 701795 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4677. Min Act: -0.0000

Data Index: 627078 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1224656 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4281. Min Act: -0.0000

Data Index: 357529 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4148. Min Act: -0.0000

Data Index: 67599 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4325. Min Act: -0.0000

Data Index: 315549 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1263644 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.3961. Min Act: -0.0000

Data Index: 313751 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.7699. Min Range: -0.7699

Max Act: 0.4042. Min Act: -0.0000

Data Index: 330894 (C4 (Web Text))

Max Activating Token Index: 198