Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1896 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.5871. Min Act: -0.0003

Data Index: 767116 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4735. Min Act: -0.0003

Data Index: 77067 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4717. Min Act: -0.0003

Data Index: 962129 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4523. Min Act: -0.0003

Data Index: 1190300 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4523. Min Act: -0.0003

Data Index: 853692 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4410. Min Act: -0.0003

Data Index: 243467 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4422. Min Act: -0.0003

Data Index: 1073891 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4546. Min Act: -0.0003

Data Index: 471744 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4495. Min Act: -0.0003

Data Index: 238289 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4685. Min Act: -0.0003

Data Index: 584075 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4303. Min Act: -0.0003

Data Index: 1314467 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4544. Min Act: -0.0003

Data Index: 436320 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4228. Min Act: -0.0003

Data Index: 820042 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4563. Min Act: -0.0003

Data Index: 147134 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4526. Min Act: -0.0003

Data Index: 1162183 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4461. Min Act: -0.0003

Data Index: 453919 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4286. Min Act: -0.0003

Data Index: 628167 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4126. Min Act: -0.0003

Data Index: 444002 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4476. Min Act: -0.0003

Data Index: 805344 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.5871. Min Range: -0.5871

Max Act: 0.4270. Min Act: -0.0003

Data Index: 772051 (C4 (Web Text))

Max Activating Token Index: 117