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

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

Neuron 1578 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: 2.5079. Min Range: -2.5079

Max Act: 2.5079. Min Act: -0.0000

Data Index: 166523 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0918. Min Act: -0.0000

Data Index: 322569 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.2849. Min Act: -0.0000

Data Index: 924727 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.8533. Min Act: -0.0000

Data Index: 620319 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9162. Min Act: -0.0000

Data Index: 176307 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9571. Min Act: -0.0000

Data Index: 676928 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9567. Min Act: -0.0000

Data Index: 412746 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.6411. Min Act: -0.0000

Data Index: 706247 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.8022. Min Act: -0.0000

Data Index: 156655 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9992. Min Act: -0.0000

Data Index: 263906 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.8041. Min Act: -0.0000

Data Index: 134409 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.6833. Min Act: -0.0000

Data Index: 1227498 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.7567. Min Act: -0.0000

Data Index: 497256 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.7656. Min Act: -0.0000

Data Index: 678670 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.7458. Min Act: -0.0000

Data Index: 836331 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.8569. Min Act: -0.0000

Data Index: 139233 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.7156. Min Act: -0.0000

Data Index: 867868 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.6410. Min Act: -0.0000

Data Index: 46475 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.6078. Min Act: -0.0000

Data Index: 383412 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.6978. Min Act: -0.0000

Data Index: 49223 (C4 (Web Text))

Max Activating Token Index: 958