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

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

Neuron 755 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0957. Min Range: -1.0957

Max Act: 1.0957. Min Act: -0.0000

Data Index: 579746 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9633. Min Act: -0.0000

Data Index: 115154 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9991. Min Act: -0.0000

Data Index: 205111 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1170933 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1191938 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8740. Min Act: -0.0000

Data Index: 371315 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8524. Min Act: -0.0000

Data Index: 774162 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8615. Min Act: -0.0000

Data Index: 349691 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8229. Min Act: -0.0000

Data Index: 532705 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1018309 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8277. Min Act: -0.0000

Data Index: 144533 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.7246. Min Act: -0.0000

Data Index: 798336 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.8028. Min Act: -0.0000

Data Index: 864559 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.6875. Min Act: -0.0000

Data Index: 593728 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1085646 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1268594 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.7980. Min Act: -0.0000

Data Index: 499123 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1241515 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.7099. Min Act: -0.0000

Data Index: 811319 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 1.0957. Min Range: -1.0957

Max Act: 0.6461. Min Act: -0.0000

Data Index: 83276 (C4 (Web Text))

Max Activating Token Index: 496