Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2868 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.9456. Min Act: -0.0000

Data Index: 293057 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.8277. Min Act: -0.0000

Data Index: 350211 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.8576. Min Act: -0.0000

Data Index: 587484 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7864. Min Act: -0.0000

Data Index: 578302 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7814. Min Act: -0.0001

Data Index: 1371201 (Python Code)

Max Activating Token Index: 622

Text #5

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1216271 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7698. Min Act: -0.0000

Data Index: 717952 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7672. Min Act: -0.0000

Data Index: 319851 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7580. Min Act: -0.0000

Data Index: 659225 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7637. Min Act: -0.0000

Data Index: 1052811 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1517537 (Python Code)

Max Activating Token Index: 999

Text #11

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7567. Min Act: -0.0001

Data Index: 316236 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7437. Min Act: -0.0000

Data Index: 956704 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7530. Min Act: -0.0000

Data Index: 518995 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7482. Min Act: -0.0000

Data Index: 448152 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7468. Min Act: -0.0001

Data Index: 1573085 (Python Code)

Max Activating Token Index: 893

Text #16

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7399. Min Act: -0.0000

Data Index: 187418 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7344. Min Act: -0.0001

Data Index: 1425637 (Python Code)

Max Activating Token Index: 578

Text #18

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.7006. Min Act: -0.0001

Data Index: 1563363 (Python Code)

Max Activating Token Index: 939

Text #19

Max Range: 0.9456. Min Range: -0.9456

Max Act: 0.6565. Min Act: -0.0001

Data Index: 1577735 (Python Code)

Max Activating Token Index: 396