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

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

Neuron 4061 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: 0.4090. Min Range: -0.4090

Max Act: 0.4090. Min Act: -0.0001

Data Index: 44939 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3601. Min Act: -0.0001

Data Index: 679002 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1251553 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1094908 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3312. Min Act: -0.0001

Data Index: 220834 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3174. Min Act: -0.0001

Data Index: 355614 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1083984 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3149. Min Act: -0.0001

Data Index: 268222 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3093. Min Act: -0.0001

Data Index: 315507 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2977. Min Act: -0.0001

Data Index: 652540 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3068. Min Act: -0.0001

Data Index: 930380 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3067. Min Act: -0.0001

Data Index: 329971 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.3016. Min Act: -0.0001

Data Index: 104518 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2718. Min Act: -0.0001

Data Index: 563040 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2918. Min Act: -0.0001

Data Index: 985117 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2968. Min Act: -0.0000

Data Index: 795101 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2939. Min Act: -0.0000

Data Index: 493100 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1325388 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2795. Min Act: -0.0001

Data Index: 519709 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.4090. Min Range: -0.4090

Max Act: 0.2795. Min Act: -0.0001

Data Index: 738353 (C4 (Web Text))

Max Activating Token Index: 2