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

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

Neuron 3211 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: 3.3367. Min Range: -3.3367

Max Act: 3.3367. Min Act: -0.0000

Data Index: 1342704 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.9249. Min Act: -0.0000

Data Index: 932217 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.8804. Min Act: -0.0001

Data Index: 436423 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.7781. Min Act: -0.0000

Data Index: 662227 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.7574. Min Act: -0.0000

Data Index: 621364 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.9555. Min Act: -0.0000

Data Index: 580523 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.5486. Min Act: -0.0001

Data Index: 974873 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.7513. Min Act: -0.0001

Data Index: 252231 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.5692. Min Act: -0.0000

Data Index: 858830 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.5592. Min Act: -0.0001

Data Index: 125017 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.6589. Min Act: -0.0000

Data Index: 500344 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.5148. Min Act: -0.0001

Data Index: 597662 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.6324. Min Act: -0.0001

Data Index: 1142681 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.2157. Min Act: -0.0000

Data Index: 210622 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.2397. Min Act: -0.0000

Data Index: 217644 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.1456. Min Act: -0.0001

Data Index: 1110063 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.2517. Min Act: -0.0001

Data Index: 1162072 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.1453. Min Act: -0.0001

Data Index: 384509 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.2550. Min Act: -0.0001

Data Index: 422099 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.3367. Min Range: -3.3367

Max Act: 2.0306. Min Act: -0.0001

Data Index: 967401 (C4 (Web Text))

Max Activating Token Index: 333