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

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

Neuron 5685 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.8970. Min Act: -0.0000

Data Index: 459445 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.7719. Min Act: -0.0000

Data Index: 278036 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.5415. Min Act: -0.0000

Data Index: 63786 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.4781. Min Act: -0.0000

Data Index: 893445 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.4811. Min Act: -0.0000

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.5467. Min Act: 0.0000

Data Index: 933693 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.3229. Min Act: -0.0000

Data Index: 910101 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.2972. Min Act: -0.0000

Data Index: 1040668 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.2728. Min Act: -0.0000

Data Index: 885113 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.1438. Min Act: -0.0000

Data Index: 1019715 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.0953. Min Act: -0.0000

Data Index: 225765 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1187492 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.1805. Min Act: -0.0000

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.2824. Min Act: -0.0000

Data Index: 145212 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.2705. Min Act: -0.0000

Data Index: 685873 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.1665. Min Act: 0.0000

Data Index: 1297528 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.1547. Min Act: 0.0000

Data Index: 329214 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.0149. Min Act: 0.0000

Data Index: 1097940 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.2393. Min Act: -0.0000

Data Index: 244809 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 2.8970. Min Range: -2.8970

Max Act: 2.0605. Min Act: -0.0000

Data Index: 352544 (C4 (Web Text))

Max Activating Token Index: 681