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

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

Neuron 4444 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0001

Data Index: 747605 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1358894 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0515. Min Act: -0.0001

Data Index: 480286 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1256347 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0546. Min Act: -0.0001

Data Index: 432916 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0537. Min Act: -0.0001

Data Index: 532295 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0509. Min Act: -0.0001

Data Index: 405550 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1334264 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0473. Min Act: -0.0001

Data Index: 657803 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1095629 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0479. Min Act: -0.0001

Data Index: 351539 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0382. Min Act: -0.0001

Data Index: 163268 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0435. Min Act: -0.0001

Data Index: 765772 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0460. Min Act: -0.0001

Data Index: 975567 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1170229 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0440. Min Act: -0.0001

Data Index: 532420 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0436. Min Act: -0.0001

Data Index: 661558 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0429. Min Act: -0.0001

Data Index: 163893 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0438. Min Act: -0.0001

Data Index: 310961 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0423. Min Act: -0.0001

Data Index: 909411 (C4 (Web Text))

Max Activating Token Index: 229