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

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

Neuron 3159 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.6317. Min Act: -0.0003

Data Index: 705315 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4837. Min Act: -0.0003

Data Index: 660600 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5459. Min Act: -0.0003

Data Index: 203189 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5133. Min Act: -0.0003

Data Index: 1200688 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5622. Min Act: -0.0003

Data Index: 144717 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4935. Min Act: -0.0003

Data Index: 805395 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4957. Min Act: -0.0003

Data Index: 717955 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4912. Min Act: -0.0003

Data Index: 1254754 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5249. Min Act: -0.0003

Data Index: 1091633 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5559. Min Act: -0.0003

Data Index: 224141 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4569. Min Act: -0.0003

Data Index: 823554 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5163. Min Act: -0.0003

Data Index: 1306811 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5454. Min Act: -0.0003

Data Index: 1002973 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4769. Min Act: -0.0003

Data Index: 277518 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5778. Min Act: -0.0003

Data Index: 558343 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4760. Min Act: -0.0003

Data Index: 44438 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5079. Min Act: -0.0003

Data Index: 817066 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.5741. Min Act: -0.0003

Data Index: 106880 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4578. Min Act: -0.0003

Data Index: 137379 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.6317. Min Range: -0.6317

Max Act: 0.4413. Min Act: -0.0003

Data Index: 125404 (C4 (Web Text))

Max Activating Token Index: 580