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

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

Neuron 2368 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: 0.3946. Min Range: -0.3946

Max Act: 0.3946. Min Act: -0.0001

Data Index: 533344 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3741. Min Act: -0.0001

Data Index: 401216 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3657. Min Act: -0.0001

Data Index: 1106514 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3581. Min Act: -0.0001

Data Index: 478596 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3293. Min Act: -0.0001

Data Index: 869966 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3376. Min Act: -0.0001

Data Index: 747320 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3198. Min Act: -0.0001

Data Index: 614067 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3401. Min Act: -0.0001

Data Index: 1109551 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2973. Min Act: -0.0001

Data Index: 531613 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2953. Min Act: -0.0001

Data Index: 987001 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2838. Min Act: -0.0001

Data Index: 392001 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2822. Min Act: -0.0001

Data Index: 1172979 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1202156 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1046153 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2976. Min Act: -0.0001

Data Index: 536525 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2892. Min Act: -0.0001

Data Index: 1077214 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2833. Min Act: -0.0001

Data Index: 855439 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2926. Min Act: -0.0001

Data Index: 34431 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1151348 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.3946. Min Range: -0.3946

Max Act: 0.3107. Min Act: -0.0001

Data Index: 1256009 (C4 (Web Text))

Max Activating Token Index: 613