Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3980 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.4769. Min Range: -6.4769

Max Act: 6.4769. Min Act: -0.0000

Data Index: 921680 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 6.4769. Min Range: -6.4769

Max Act: 6.3083. Min Act: -0.0000

Data Index: 1235433 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 6.4769. Min Range: -6.4769

Max Act: 6.4129. Min Act: -0.0000

Data Index: 429155 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 6.4769. Min Range: -6.4769

Max Act: 6.0601. Min Act: -0.0000

Data Index: 74804 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 6.4769. Min Range: -6.4769

Max Act: 5.8086. Min Act: -0.0000

Data Index: 679396 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 6.4769. Min Range: -6.4769

Max Act: 5.5917. Min Act: -0.0000

Data Index: 522103 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 6.4769. Min Range: -6.4769

Max Act: 5.5037. Min Act: -0.0000

Data Index: 706461 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 6.4769. Min Range: -6.4769

Max Act: 5.3277. Min Act: -0.0000

Data Index: 1241546 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 6.4769. Min Range: -6.4769

Max Act: 5.0431. Min Act: -0.0000

Data Index: 972689 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 6.4769. Min Range: -6.4769

Max Act: 5.2587. Min Act: -0.0000

Data Index: 930939 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.9719. Min Act: -0.0000

Data Index: 120181 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 6.4769. Min Range: -6.4769

Max Act: 5.3202. Min Act: -0.0000

Data Index: 678732 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.8038. Min Act: -0.0000

Data Index: 1191066 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.7489. Min Act: -0.0000

Data Index: 482578 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.6937. Min Act: -0.0000

Data Index: 1035502 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.4821. Min Act: -0.0000

Data Index: 1238961 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.4407. Min Act: -0.0000

Data Index: 1198264 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.6687. Min Act: -0.0000

Data Index: 124826 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.2455. Min Act: -0.0000

Data Index: 1209307 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 6.4769. Min Range: -6.4769

Max Act: 4.5091. Min Act: -0.0000

Data Index: 389814 (C4 (Web Text))

Max Activating Token Index: 585