Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 337 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4864. Min Act: -0.0001

Data Index: 918763 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4854. Min Act: -0.0001

Data Index: 327493 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1200305 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4237. Min Act: -0.0001

Data Index: 466377 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4339. Min Act: -0.0001

Data Index: 1068424 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4462. Min Act: -0.0001

Data Index: 1166354 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4027. Min Act: -0.0001

Data Index: 340874 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4465. Min Act: -0.0001

Data Index: 483305 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4304. Min Act: -0.0001

Data Index: 264319 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4247. Min Act: -0.0001

Data Index: 103228 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4205. Min Act: -0.0001

Data Index: 772519 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4159. Min Act: -0.0001

Data Index: 1098956 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4030. Min Act: -0.0001

Data Index: 292895 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4012. Min Act: -0.0001

Data Index: 395474 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1021003 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4283. Min Act: -0.0001

Data Index: 1156786 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4129. Min Act: -0.0001

Data Index: 118475 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4115. Min Act: -0.0001

Data Index: 68514 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.3985. Min Act: -0.0001

Data Index: 359183 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.4864. Min Range: -0.4864

Max Act: 0.4088. Min Act: -0.0001

Data Index: 165774 (C4 (Web Text))

Max Activating Token Index: 309