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

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

Neuron 5406 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3246. Min Range: -5.3246

Max Act: 5.3246. Min Act: -0.0000

Data Index: 86664 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.9679. Min Act: -0.0000

Data Index: 826062 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.6830. Min Act: -0.0000

Data Index: 537562 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.4893. Min Act: -0.0000

Data Index: 832443 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.6075. Min Act: -0.0000

Data Index: 1132446 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.3306. Min Act: -0.0000

Data Index: 553692 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.0688. Min Act: -0.0000

Data Index: 735371 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.0469. Min Act: -0.0000

Data Index: 1162253 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.9915. Min Act: -0.0000

Data Index: 1136800 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.8542. Min Act: -0.0000

Data Index: 73616 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.6406. Min Act: -0.0000

Data Index: 446859 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.6027. Min Act: -0.0000

Data Index: 253071 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.6422. Min Act: -0.0000

Data Index: 940607 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.4428. Min Act: -0.0000

Data Index: 76457 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.5215. Min Act: 0.0000

Data Index: 951665 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.4505. Min Act: -0.0000

Data Index: 806372 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.4196. Min Act: -0.0000

Data Index: 766043 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.3596. Min Act: -0.0000

Data Index: 1356526 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.2823. Min Act: -0.0000

Data Index: 935626 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.1928. Min Act: -0.0000

Data Index: 1300902 (C4 (Web Text))

Max Activating Token Index: 402