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

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

Neuron 1320 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: 1.7231. Min Range: -1.7231

Max Act: 1.7134. Min Act: -0.0000

Data Index: 759919 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.7231. Min Act: -0.0000

Data Index: 1109552 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6653. Min Act: -0.0000

Data Index: 426402 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6281. Min Act: -0.0000

Data Index: 538654 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6426. Min Act: -0.0000

Data Index: 480956 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6747. Min Act: -0.0000

Data Index: 452499 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5947. Min Act: -0.0000

Data Index: 532738 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6187. Min Act: -0.0000

Data Index: 1340472 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6744. Min Act: -0.0000

Data Index: 1075697 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5197. Min Act: -0.0000

Data Index: 451250 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1052864 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1325671 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4651. Min Act: -0.0000

Data Index: 303267 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4456. Min Act: -0.0000

Data Index: 770395 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3443. Min Act: -0.0000

Data Index: 533030 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1207380 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3978. Min Act: -0.0000

Data Index: 894713 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3740. Min Act: -0.0000

Data Index: 169495 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.2835. Min Act: -0.0000

Data Index: 603615 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3443. Min Act: -0.0000

Data Index: 108716 (C4 (Web Text))

Max Activating Token Index: 511