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

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

Neuron 2340 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.4079. Min Act: -0.0000

Data Index: 537751 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.4035. Min Act: -0.0000

Data Index: 366707 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.2937. Min Act: -0.0000

Data Index: 585685 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.5437. Min Act: -0.0000

Data Index: 1343072 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.2858. Min Act: -0.0000

Data Index: 597586 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.2622. Min Act: -0.0000

Data Index: 1090489 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.0832. Min Act: -0.0000

Data Index: 618758 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1049770 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 2.5437. Min Range: -2.5437

Max Act: 2.1712. Min Act: -0.0000

Data Index: 28856 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.6952. Min Act: -0.0000

Data Index: 1045674 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.5867. Min Act: -0.0000

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.7264. Min Act: -0.0000

Data Index: 949896 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.7363. Min Act: -0.0000

Data Index: 888872 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.6514. Min Act: -0.0000

Data Index: 248856 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.4307. Min Act: -0.0000

Data Index: 1048796 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1052895 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.5782. Min Act: -0.0000

Data Index: 575000 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.4299. Min Act: -0.0000

Data Index: 454661 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.5164. Min Act: -0.0000

Data Index: 1015065 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 2.5437. Min Range: -2.5437

Max Act: 1.3713. Min Act: -0.0000

Data Index: 340663 (C4 (Web Text))

Max Activating Token Index: 272