Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2674 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1271439 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1161. Min Act: -0.0001

Data Index: 925226 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1111. Min Act: -0.0001

Data Index: 19751 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1159. Min Act: -0.0001

Data Index: 530000 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1634971 (Python Code)

Max Activating Token Index: 663

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0971. Min Act: -0.0001

Data Index: 244477 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1052. Min Act: -0.0001

Data Index: 599991 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1013775 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0960. Min Act: -0.0001

Data Index: 993371 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0790. Min Act: -0.0001

Data Index: 326691 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0902. Min Act: -0.0001

Data Index: 52150 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1009791 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1414504 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0944. Min Act: -0.0001

Data Index: 396589 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0928. Min Act: -0.0001

Data Index: 194807 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1577674 (Python Code)

Max Activating Token Index: 662

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0927. Min Act: -0.0001

Data Index: 1375117 (Python Code)

Max Activating Token Index: 796

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1205008 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1017. Min Act: -0.0001

Data Index: 622232 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.0810. Min Act: -0.0001

Data Index: 932639 (C4 (Web Text))

Max Activating Token Index: 836