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

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

Neuron 723 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.3442. Min Range: -4.3442

Max Act: 4.3442. Min Act: -0.0000

Data Index: 554091 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 4.3442. Min Range: -4.3442

Max Act: 3.6194. Min Act: -0.0000

Data Index: 689449 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 4.3442. Min Range: -4.3442

Max Act: 3.3284. Min Act: -0.0000

Data Index: 540110 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 4.3442. Min Range: -4.3442

Max Act: 3.0869. Min Act: -0.0000

Data Index: 1022313 (C4 (Web Text))

Max Activating Token Index: 282

Text #4

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.4787. Min Act: -0.0000

Data Index: 559864 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.3528. Min Act: -0.0000

Data Index: 817784 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.2666. Min Act: -0.0000

Data Index: 3924 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.0318. Min Act: -0.0000

Data Index: 249819 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.9897. Min Act: -0.0000

Data Index: 226841 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.9550. Min Act: -0.0000

Data Index: 881111 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1055967 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.9419. Min Act: -0.0000

Data Index: 550183 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.8950. Min Act: -0.0000

Data Index: 1259745 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.0042. Min Act: -0.0000

Data Index: 1326722 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.8866. Min Act: -0.0000

Data Index: 12415 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.9763. Min Act: -0.0000

Data Index: 974800 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.9716. Min Act: -0.0000

Data Index: 235359 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 4.3442. Min Range: -4.3442

Max Act: 1.9519. Min Act: -0.0000

Data Index: 1038690 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.0653. Min Act: -0.0000

Data Index: 1231787 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 4.3442. Min Range: -4.3442

Max Act: 2.0642. Min Act: -0.0000

Data Index: 1104110 (C4 (Web Text))

Max Activating Token Index: 587