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

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

Neuron 2159 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0331. Min Range: -1.0331

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1101699 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 1.0331. Min Range: -1.0331

Max Act: 1.0331. Min Act: -0.0000

Data Index: 509071 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.9882. Min Act: -0.0000

Data Index: 447326 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.0331. Min Range: -1.0331

Max Act: 1.0070. Min Act: -0.0000

Data Index: 1004109 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.9407. Min Act: -0.0000

Data Index: 337354 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8963. Min Act: -0.0000

Data Index: 728061 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8852. Min Act: -0.0000

Data Index: 274465 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1313753 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7788. Min Act: -0.0000

Data Index: 975603 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1124196 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1185647 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7999. Min Act: -0.0000

Data Index: 22672 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7775. Min Act: -0.0000

Data Index: 464325 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1078184 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1105364 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7194. Min Act: -0.0000

Data Index: 484034 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1116739 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7350. Min Act: -0.0000

Data Index: 166582 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7225. Min Act: -0.0000

Data Index: 351930 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7649. Min Act: -0.0000

Data Index: 73097 (C4 (Web Text))

Max Activating Token Index: 974