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

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

Neuron 6075 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: 4.7703. Min Range: -4.7703

Max Act: 4.5990. Min Act: -0.0000

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 4.7703. Min Range: -4.7703

Max Act: 4.7703. Min Act: -0.0001

Data Index: 647034 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 4.7703. Min Range: -4.7703

Max Act: 4.1300. Min Act: -0.0000

Data Index: 839420 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 4.7703. Min Range: -4.7703

Max Act: 3.1961. Min Act: -0.0001

Data Index: 359312 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.4964. Min Act: -0.0000

Data Index: 1333548 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.6721. Min Act: -0.0001

Data Index: 657359 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.5643. Min Act: -0.0001

Data Index: 459193 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.4625. Min Act: -0.0000

Data Index: 893610 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.1819. Min Act: -0.0000

Data Index: 289827 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.3796. Min Act: -0.0000

Data Index: 307477 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.4863. Min Act: -0.0000

Data Index: 1334038 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.5790. Min Act: -0.0000

Data Index: 194673 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.2408. Min Act: -0.0001

Data Index: 936104 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.3446. Min Act: -0.0001

Data Index: 854962 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.3246. Min Act: -0.0001

Data Index: 622534 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.3084. Min Act: -0.0000

Data Index: 509401 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 4.7703. Min Range: -4.7703

Max Act: 1.9845. Min Act: -0.0000

Data Index: 408356 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.4810. Min Act: -0.0001

Data Index: 1124617 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 4.7703. Min Range: -4.7703

Max Act: 2.2355. Min Act: -0.0000

Data Index: 1034474 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 4.7703. Min Range: -4.7703

Max Act: 1.9984. Min Act: -0.0000

Data Index: 554123 (C4 (Web Text))

Max Activating Token Index: 490