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

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

Neuron 1605 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.6166. Min Act: -0.0004

Data Index: 831459 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.6016. Min Act: -0.0004

Data Index: 564703 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5427. Min Act: -0.0004

Data Index: 595634 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5144. Min Act: -0.0004

Data Index: 1325324 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4643. Min Act: -0.0004

Data Index: 137474 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5182. Min Act: -0.0004

Data Index: 95945 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5351. Min Act: -0.0004

Data Index: 594044 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5711. Min Act: -0.0004

Data Index: 1055934 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5882. Min Act: -0.0004

Data Index: 650177 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4632. Min Act: -0.0004

Data Index: 819070 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.3694. Min Act: -0.0004

Data Index: 727004 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5043. Min Act: -0.0004

Data Index: 744888 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4411. Min Act: -0.0004

Data Index: 257145 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5222. Min Act: -0.0004

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.6471. Min Act: -0.0004

Data Index: 447292 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5187. Min Act: -0.0004

Data Index: 669979 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.3977. Min Act: -0.0004

Data Index: 718857 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.5541. Min Act: -0.0004

Data Index: 958841 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4504. Min Act: -0.0004

Data Index: 1095147 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.6471. Min Range: -0.6471

Max Act: 0.4817. Min Act: -0.0004

Data Index: 591774 (C4 (Web Text))

Max Activating Token Index: 623