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

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

Neuron 4517 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: 0.6417. Min Range: -0.6417

Max Act: 0.6417. Min Act: -0.0000

Data Index: 85688 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5366. Min Act: -0.0000

Data Index: 787034 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5517. Min Act: -0.0000

Data Index: 997526 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5114. Min Act: -0.0000

Data Index: 236258 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5147. Min Act: -0.0000

Data Index: 740337 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5103. Min Act: -0.0000

Data Index: 329909 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4685. Min Act: -0.0000

Data Index: 505099 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4861. Min Act: -0.0000

Data Index: 232351 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4837. Min Act: -0.0000

Data Index: 753648 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1183613 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4908. Min Act: -0.0000

Data Index: 816979 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.5029. Min Act: -0.0000

Data Index: 329772 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4639. Min Act: -0.0000

Data Index: 72570 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1017731 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4624. Min Act: -0.0000

Data Index: 725174 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4632. Min Act: -0.0000

Data Index: 550357 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1237461 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4818. Min Act: -0.0000

Data Index: 286263 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4346. Min Act: -0.0000

Data Index: 805853 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.6417. Min Range: -0.6417

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1342290 (C4 (Web Text))

Max Activating Token Index: 864