Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2451 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.9265. Min Act: -0.0001

Data Index: 1163716 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4988. Min Act: -0.0001

Data Index: 193688 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.8114. Min Act: -0.0001

Data Index: 766505 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.5340. Min Act: -0.0001

Data Index: 249130 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.5134. Min Act: -0.0001

Data Index: 675180 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.5740. Min Act: -0.0001

Data Index: 830566 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.6120. Min Act: -0.0001

Data Index: 1345128 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4510. Min Act: -0.0001

Data Index: 313322 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4829. Min Act: -0.0001

Data Index: 961316 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4233. Min Act: -0.0001

Data Index: 516796 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.5024. Min Act: -0.0001

Data Index: 446958 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4064. Min Act: -0.0001

Data Index: 1032110 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4343. Min Act: -0.0001

Data Index: 1246615 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2962. Min Act: -0.0001

Data Index: 1248945 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4507. Min Act: -0.0001

Data Index: 1286003 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.3208. Min Act: -0.0001

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2769. Min Act: -0.0001

Data Index: 1119477 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.3576. Min Act: -0.0001

Data Index: 491523 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2650. Min Act: -0.0001

Data Index: 1037996 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.4525. Min Act: -0.0001

Data Index: 557789 (C4 (Web Text))

Max Activating Token Index: 636