Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2051 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.0807. Min Range: -5.0807

Max Act: 5.0807. Min Act: -0.0000

Data Index: 791368 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 5.0807. Min Range: -5.0807

Max Act: 4.7944. Min Act: -0.0000

Data Index: 834901 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 5.0807. Min Range: -5.0807

Max Act: 4.6412. Min Act: -0.0000

Data Index: 985238 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 5.0807. Min Range: -5.0807

Max Act: 4.6046. Min Act: -0.0000

Data Index: 1253460 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 5.0807. Min Range: -5.0807

Max Act: 4.2378. Min Act: -0.0000

Data Index: 1047730 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 5.0807. Min Range: -5.0807

Max Act: 4.2146. Min Act: -0.0000

Data Index: 303551 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 5.0807. Min Range: -5.0807

Max Act: 4.0640. Min Act: -0.0000

Data Index: 765481 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.8737. Min Act: -0.0000

Data Index: 891571 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 5.0807. Min Range: -5.0807

Max Act: 4.0710. Min Act: -0.0000

Data Index: 456636 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.6385. Min Act: -0.0000

Data Index: 46475 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.6716. Min Act: -0.0000

Data Index: 406790 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.6541. Min Act: -0.0000

Data Index: 863346 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.5934. Min Act: -0.0000

Data Index: 152239 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.5961. Min Act: -0.0000

Data Index: 890540 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.5956. Min Act: -0.0000

Data Index: 681506 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.5549. Min Act: -0.0000

Data Index: 1305611 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.2678. Min Act: -0.0000

Data Index: 1298498 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.5682. Min Act: -0.0000

Data Index: 683593 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.4156. Min Act: -0.0000

Data Index: 3718 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 5.0807. Min Range: -5.0807

Max Act: 3.6990. Min Act: -0.0000

Data Index: 592991 (C4 (Web Text))

Max Activating Token Index: 210