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

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

Neuron 2726 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: 2.8436. Min Range: -2.8436

Max Act: 2.8148. Min Act: -0.0000

Data Index: 185205 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.8436. Min Act: -0.0000

Data Index: 207714 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.7793. Min Act: -0.0000

Data Index: 318046 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.6257. Min Act: -0.0000

Data Index: 20207 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.7344. Min Act: -0.0000

Data Index: 64995 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.7203. Min Act: -0.0000

Data Index: 1196649 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.7064. Min Act: -0.0000

Data Index: 1199072 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.6688. Min Act: -0.0000

Data Index: 1177161 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.7973. Min Act: -0.0000

Data Index: 597159 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.4734. Min Act: -0.0000

Data Index: 442491 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.6163. Min Act: -0.0000

Data Index: 889522 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.5923. Min Act: -0.0000

Data Index: 107726 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.7339. Min Act: -0.0000

Data Index: 948640 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.4132. Min Act: -0.0000

Data Index: 480278 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.3711. Min Act: -0.0000

Data Index: 740870 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.6201. Min Act: -0.0000

Data Index: 653034 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1046535 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.5841. Min Act: -0.0000

Data Index: 1230684 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.5439. Min Act: -0.0000

Data Index: 52923 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 2.8436. Min Range: -2.8436

Max Act: 2.5780. Min Act: -0.0000

Data Index: 371654 (C4 (Web Text))

Max Activating Token Index: 705