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

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

Neuron 1683 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6534. Min Range: -4.6534

Max Act: 4.6534. Min Act: -0.0000

Data Index: 1107269 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 4.6534. Min Range: -4.6534

Max Act: 3.3249. Min Act: -0.0000

Data Index: 1026759 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 4.6534. Min Range: -4.6534

Max Act: 3.0122. Min Act: -0.0000

Data Index: 629523 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 4.6534. Min Range: -4.6534

Max Act: 3.0556. Min Act: -0.0000

Data Index: 519992 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.8576. Min Act: -0.0000

Data Index: 281437 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.4218. Min Act: -0.0000

Data Index: 1285210 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.3793. Min Act: -0.0000

Data Index: 1149126 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.4037. Min Act: -0.0000

Data Index: 356598 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.4010. Min Act: -0.0000

Data Index: 336602 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.4211. Min Act: -0.0000

Data Index: 594197 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.3918. Min Act: -0.0000

Data Index: 1235803 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.2120. Min Act: -0.0000

Data Index: 1026654 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.4289. Min Act: -0.0000

Data Index: 189970 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.4355. Min Act: -0.0000

Data Index: 544183 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.3102. Min Act: -0.0000

Data Index: 490908 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.2952. Min Act: -0.0000

Data Index: 1336001 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.1651. Min Act: -0.0000

Data Index: 799820 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.2417. Min Act: -0.0000

Data Index: 1295645 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.2506. Min Act: -0.0000

Data Index: 332560 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 4.6534. Min Range: -4.6534

Max Act: 2.3588. Min Act: -0.0000

Data Index: 176892 (C4 (Web Text))

Max Activating Token Index: 813