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

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

Neuron 2444 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4066. Min Range: -3.4066

Max Act: 3.4066. Min Act: -0.0000

Data Index: 967918 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 3.4066. Min Range: -3.4066

Max Act: 3.1065. Min Act: -0.0000

Data Index: 284722 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.8098. Min Act: -0.0000

Data Index: 1162445 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.8929. Min Act: -0.0000

Data Index: 771699 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 3.4066. Min Range: -3.4066

Max Act: 3.0094. Min Act: -0.0000

Data Index: 434578 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.5434. Min Act: -0.0000

Data Index: 545641 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.6670. Min Act: -0.0000

Data Index: 89392 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.6094. Min Act: -0.0000

Data Index: 333278 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.4322. Min Act: -0.0000

Data Index: 481156 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.5724. Min Act: -0.0000

Data Index: 1128056 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.6668. Min Act: -0.0000

Data Index: 410104 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.6460. Min Act: -0.0000

Data Index: 992304 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.4479. Min Act: -0.0000

Data Index: 436007 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.3138. Min Act: -0.0000

Data Index: 784527 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.4343. Min Act: -0.0000

Data Index: 580908 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.1530. Min Act: -0.0000

Data Index: 709499 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.3813. Min Act: -0.0000

Data Index: 665294 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.2589. Min Act: -0.0000

Data Index: 898208 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.3414. Min Act: -0.0000

Data Index: 444063 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.4066. Min Range: -3.4066

Max Act: 2.2342. Min Act: -0.0000

Data Index: 597084 (C4 (Web Text))

Max Activating Token Index: 134