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

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

Neuron 1107 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: 0.3226. Min Range: -0.3226

Max Act: 0.3050. Min Act: -0.0000

Data Index: 787737 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2946. Min Act: -0.0000

Data Index: 760332 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1038652 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3226. Min Act: -0.0000

Data Index: 781982 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.3119. Min Act: -0.0000

Data Index: 619138 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2791. Min Act: -0.0000

Data Index: 171832 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2904. Min Act: -0.0000

Data Index: 837003 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1338567 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1170984 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1041134 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2796. Min Act: -0.0001

Data Index: 243877 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2840. Min Act: -0.0000

Data Index: 116587 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1055515 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2845. Min Act: -0.0001

Data Index: 348431 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2561. Min Act: -0.0000

Data Index: 46254 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2839. Min Act: -0.0000

Data Index: 368575 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2841. Min Act: -0.0001

Data Index: 49469 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2569. Min Act: -0.0000

Data Index: 119963 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2943. Min Act: -0.0000

Data Index: 599487 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.3226. Min Range: -0.3226

Max Act: 0.2550. Min Act: -0.0001

Data Index: 572960 (C4 (Web Text))

Max Activating Token Index: 991