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

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

Neuron 1811 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: 0.3488. Min Range: -0.3488

Max Act: 0.3371. Min Act: -0.0000

Data Index: 635233 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3488. Min Act: -0.0000

Data Index: 630124 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3470. Min Act: -0.0001

Data Index: 1212189 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1105662 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.3063. Min Act: -0.0001

Data Index: 395992 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1107185 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1081869 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1157365 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2849. Min Act: -0.0000

Data Index: 376820 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2880. Min Act: -0.0001

Data Index: 461942 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2833. Min Act: -0.0001

Data Index: 622836 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1034469 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2734. Min Act: -0.0001

Data Index: 956413 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2715. Min Act: -0.0001

Data Index: 1557179 (Python Code)

Max Activating Token Index: 572

Text #14

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2651. Min Act: -0.0000

Data Index: 918948 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2707. Min Act: -0.0001

Data Index: 785151 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2608. Min Act: -0.0000

Data Index: 805021 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2578. Min Act: -0.0001

Data Index: 697127 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2695. Min Act: -0.0001

Data Index: 595399 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.3488. Min Range: -0.3488

Max Act: 0.2489. Min Act: -0.0001

Data Index: 443163 (C4 (Web Text))

Max Activating Token Index: 255