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

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

Neuron 475 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: 1.7419. Min Range: -1.7419

Max Act: 1.7419. Min Act: -0.0000

Data Index: 1302659 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3004. Min Act: -0.0000

Data Index: 688678 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3294. Min Act: -0.0000

Data Index: 406957 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2693. Min Act: -0.0000

Data Index: 10646 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2641. Min Act: -0.0000

Data Index: 525481 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1018254 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3126. Min Act: -0.0000

Data Index: 712261 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1977. Min Act: -0.0000

Data Index: 95349 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1192. Min Act: -0.0000

Data Index: 432742 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2414. Min Act: -0.0000

Data Index: 253502 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1071326 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1297. Min Act: -0.0000

Data Index: 1023969 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1284838 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1040. Min Act: -0.0000

Data Index: 336228 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.0433. Min Act: -0.0000

Data Index: 1107585 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.0613. Min Act: -0.0000

Data Index: 80009 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1079. Min Act: -0.0000

Data Index: 806645 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.7419. Min Range: -1.7419

Max Act: 0.9484. Min Act: -0.0000

Data Index: 681087 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.0418. Min Act: -0.0000

Data Index: 759053 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 1.7419. Min Range: -1.7419

Max Act: 0.9923. Min Act: -0.0000

Data Index: 527762 (C4 (Web Text))

Max Activating Token Index: 60