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

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

Neuron 5847 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4711. Min Range: -2.4711

Max Act: 2.4711. Min Act: -0.0000

Data Index: 491540 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.9484. Min Act: -0.0000

Data Index: 583305 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.9004. Min Act: -0.0000

Data Index: 1208148 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 2.4711. Min Range: -2.4711

Max Act: 2.1155. Min Act: -0.0000

Data Index: 924600 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.9690. Min Act: -0.0000

Data Index: 1266606 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.8491. Min Act: -0.0000

Data Index: 1071490 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 2.4711. Min Range: -2.4711

Max Act: 2.0591. Min Act: -0.0000

Data Index: 97882 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.9195. Min Act: -0.0000

Data Index: 821724 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 2.4711. Min Range: -2.4711

Max Act: 2.1052. Min Act: -0.0000

Data Index: 443232 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7863. Min Act: -0.0000

Data Index: 819070 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7700. Min Act: -0.0000

Data Index: 339817 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7466. Min Act: -0.0000

Data Index: 830295 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.8658. Min Act: -0.0000

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7286. Min Act: -0.0000

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.8459. Min Act: -0.0000

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.4711. Min Range: -2.4711

Max Act: 2.1052. Min Act: -0.0000

Data Index: 1131589 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.6883. Min Act: -0.0000

Data Index: 882420 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7788. Min Act: -0.0000

Data Index: 1092438 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7579. Min Act: -0.0000

Data Index: 1125462 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 2.4711. Min Range: -2.4711

Max Act: 1.7574. Min Act: -0.0000

Data Index: 1294413 (C4 (Web Text))

Max Activating Token Index: 518