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

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

Neuron 2891 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1485. Min Range: -2.1485

Max Act: 2.1351. Min Act: -0.0000

Data Index: 842223 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.9732. Min Act: -0.0000

Data Index: 390101 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 2.1485. Min Range: -2.1485

Max Act: 2.0177. Min Act: -0.0000

Data Index: 661032 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.1485. Min Range: -2.1485

Max Act: 2.1485. Min Act: -0.0000

Data Index: 815771 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 2.1485. Min Range: -2.1485

Max Act: 2.0187. Min Act: -0.0000

Data Index: 94629 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 2.1485. Min Range: -2.1485

Max Act: 2.0168. Min Act: -0.0000

Data Index: 1151298 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.8765. Min Act: -0.0000

Data Index: 1118752 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1331634 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.8394. Min Act: -0.0000

Data Index: 1230785 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.8211. Min Act: -0.0000

Data Index: 855932 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.8200. Min Act: -0.0000

Data Index: 764053 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1118539 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.7000. Min Act: -0.0000

Data Index: 467744 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.6890. Min Act: -0.0000

Data Index: 920451 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.7639. Min Act: -0.0000

Data Index: 392537 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.7765. Min Act: -0.0000

Data Index: 638512 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.7061. Min Act: -0.0000

Data Index: 49231 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.7099. Min Act: -0.0000

Data Index: 1159978 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.8483. Min Act: -0.0000

Data Index: 255690 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 2.1485. Min Range: -2.1485

Max Act: 1.8481. Min Act: -0.0000

Data Index: 132259 (C4 (Web Text))

Max Activating Token Index: 796