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

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

Neuron 3760 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1499693 (Python Code)

Max Activating Token Index: 359

Text #1

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1537570 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1440990 (Python Code)

Max Activating Token Index: 208

Text #3

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1633353 (Python Code)

Max Activating Token Index: 529

Text #4

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1397730 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1558836 (Python Code)

Max Activating Token Index: 565

Text #6

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1385961 (Python Code)

Max Activating Token Index: 251

Text #7

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1512342 (Python Code)

Max Activating Token Index: 124

Text #8

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1563383 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1508458 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1395379 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1373571 (Python Code)

Max Activating Token Index: 118

Text #12

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1486031 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1641063 (Python Code)

Max Activating Token Index: 160

Text #14

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1579722 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1383833 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1506117 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1368065 (Python Code)

Max Activating Token Index: 188

Text #18

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1625323 (Python Code)

Max Activating Token Index: 553

Text #19

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1436960 (Python Code)

Max Activating Token Index: 982