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

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

Neuron 2791 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.3874. Min Act: -0.0001

Data Index: 268572 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.3547. Min Act: -0.0001

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.3482. Min Act: -0.0001

Data Index: 1177298 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.2446. Min Act: -0.0001

Data Index: 469379 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.1507. Min Act: -0.0001

Data Index: 442236 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0960. Min Act: -0.0001

Data Index: 715996 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0894. Min Act: -0.0001

Data Index: 897130 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0237. Min Act: -0.0001

Data Index: 1200955 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.1076. Min Act: -0.0001

Data Index: 647963 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0482. Min Act: -0.0001

Data Index: 268378 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.1001. Min Act: -0.0001

Data Index: 452986 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0865. Min Act: -0.0001

Data Index: 1219727 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0390. Min Act: -0.0001

Data Index: 737504 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 1.3874. Min Range: -1.3874

Max Act: 0.9767. Min Act: -0.0001

Data Index: 172766 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0166. Min Act: -0.0001

Data Index: 160541 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0398. Min Act: -0.0001

Data Index: 1075723 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0337. Min Act: -0.0001

Data Index: 926689 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0692. Min Act: -0.0001

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0293. Min Act: -0.0001

Data Index: 1225944 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.3874. Min Range: -1.3874

Max Act: 1.0287. Min Act: -0.0001

Data Index: 1141130 (C4 (Web Text))

Max Activating Token Index: 684