Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.1485. Min Range: -5.1485

Max Act: 5.0100. Min Act: 0.0000

Data Index: 915285 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 5.1485. Min Range: -5.1485

Max Act: 5.1485. Min Act: -0.0000

Data Index: 146254 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.9084. Min Act: -0.0000

Data Index: 84870 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.8599. Min Act: -0.0000

Data Index: 717722 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.2531. Min Act: -0.0000

Data Index: 1311638 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.2169. Min Act: -0.0000

Data Index: 914702 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.5182. Min Act: -0.0000

Data Index: 1325737 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.8036. Min Act: -0.0000

Data Index: 354704 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.2360. Min Act: -0.0000

Data Index: 1131602 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.6365. Min Act: -0.0000

Data Index: 563065 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.2083. Min Act: -0.0000

Data Index: 1121653 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.1390. Min Act: -0.0000

Data Index: 1172971 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.2784. Min Act: -0.0000

Data Index: 215266 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.9001. Min Act: -0.0000

Data Index: 1343845 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.9076. Min Act: -0.0000

Data Index: 1193507 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.4043. Min Act: -0.0000

Data Index: 777985 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.0540. Min Act: -0.0000

Data Index: 1200603 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 5.1485. Min Range: -5.1485

Max Act: 4.1794. Min Act: -0.0000

Data Index: 92702 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.9757. Min Act: -0.0000

Data Index: 886693 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 5.1485. Min Range: -5.1485

Max Act: 3.8405. Min Act: -0.0000

Data Index: 1245974 (C4 (Web Text))

Max Activating Token Index: 509