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

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

Neuron 4510 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: 1.1782. Min Range: -1.1782

Max Act: 1.1782. Min Act: -0.0000

Data Index: 161001 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1277793 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0654. Min Act: -0.0000

Data Index: 482582 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0582. Min Act: -0.0000

Data Index: 354600 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1052722 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0421. Min Act: -0.0000

Data Index: 71264 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1018433 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0514. Min Act: -0.0000

Data Index: 934266 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1056936 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9663. Min Act: -0.0000

Data Index: 499228 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.8901. Min Act: -0.0000

Data Index: 1370210 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9875. Min Act: -0.0000

Data Index: 22997 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9794. Min Act: -0.0000

Data Index: 611842 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0371. Min Act: -0.0000

Data Index: 721102 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0327. Min Act: -0.0000

Data Index: 291016 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9469. Min Act: -0.0000

Data Index: 786151 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9422. Min Act: -0.0000

Data Index: 2772 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.1782. Min Range: -1.1782

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1314445 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9080. Min Act: -0.0000

Data Index: 640020 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 1.1782. Min Range: -1.1782

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1249113 (C4 (Web Text))

Max Activating Token Index: 996