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

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

Neuron 2265 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.9844. Min Act: -0.0001

Data Index: 4451 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.0174. Min Range: -1.0174

Max Act: 1.0174. Min Act: -0.0001

Data Index: 767540 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.9720. Min Act: -0.0001

Data Index: 925952 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.9526. Min Act: -0.0001

Data Index: 1354729 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.8459. Min Act: -0.0001

Data Index: 31516 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.8479. Min Act: -0.0001

Data Index: 1225161 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.8016. Min Act: -0.0001

Data Index: 413882 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7344. Min Act: -0.0001

Data Index: 671108 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1168414 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7693. Min Act: -0.0001

Data Index: 820715 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7227. Min Act: -0.0001

Data Index: 751436 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7521. Min Act: -0.0001

Data Index: 982189 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7486. Min Act: -0.0001

Data Index: 1270001 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7235. Min Act: -0.0001

Data Index: 534392 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.7228. Min Act: -0.0001

Data Index: 1140021 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1350538 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.6659. Min Act: -0.0001

Data Index: 797978 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.5574. Min Act: -0.0001

Data Index: 457710 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.6611. Min Act: -0.0001

Data Index: 500932 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 1.0174. Min Range: -1.0174

Max Act: 0.6636. Min Act: -0.0001

Data Index: 1126667 (C4 (Web Text))

Max Activating Token Index: 269