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

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

Neuron 3942 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.3997. Min Act: -0.0001

Data Index: 114765 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.5647. Min Act: -0.0000

Data Index: 187181 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.5082. Min Act: -0.0000

Data Index: 167112 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.3634. Min Act: -0.0001

Data Index: 1251827 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.3468. Min Act: -0.0000

Data Index: 954253 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.2740. Min Act: -0.0001

Data Index: 101643 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1581. Min Act: -0.0000

Data Index: 348467 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.2944. Min Act: -0.0000

Data Index: 31931 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1897. Min Act: -0.0001

Data Index: 1013650 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1055. Min Act: -0.0000

Data Index: 996153 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1428. Min Act: -0.0001

Data Index: 570763 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1282. Min Act: -0.0000

Data Index: 1119479 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.1831. Min Act: -0.0001

Data Index: 376451 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9790. Min Act: -0.0001

Data Index: 1355071 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.0700. Min Act: -0.0000

Data Index: 1078335 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9941. Min Act: -0.0000

Data Index: 1194548 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9964. Min Act: -0.0000

Data Index: 1005323 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9886. Min Act: -0.0000

Data Index: 1762 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 2.5647. Min Range: -2.5647

Max Act: 2.0878. Min Act: -0.0000

Data Index: 814370 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 2.5647. Min Range: -2.5647

Max Act: 1.9756. Min Act: -0.0000

Data Index: 442346 (C4 (Web Text))

Max Activating Token Index: 603