Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3071 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.2015. Min Act: -0.0001
Data Index: 1168291 (C4 (Web Text))
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1859. Min Act: -0.0001
Data Index: 721436 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1911. Min Act: -0.0001
Data Index: 725613 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1845. Min Act: -0.0001
Data Index: 1362811 (Python Code)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1729. Min Act: -0.0001
Data Index: 1040273 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1862. Min Act: -0.0001
Data Index: 967980 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1698. Min Act: -0.0001
Data Index: 1324894 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1732. Min Act: -0.0001
Data Index: 387682 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1685. Min Act: -0.0001
Data Index: 86745 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1542. Min Act: -0.0001
Data Index: 326937 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1617. Min Act: -0.0001
Data Index: 572382 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1695. Min Act: -0.0001
Data Index: 1425830 (Python Code)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1554. Min Act: -0.0001
Data Index: 21285 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1602. Min Act: -0.0001
Data Index: 1147494 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1672. Min Act: -0.0001
Data Index: 841466 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1669. Min Act: -0.0001
Data Index: 653649 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1437. Min Act: -0.0001
Data Index: 1231163 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1593. Min Act: -0.0001
Data Index: 146193 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1593. Min Act: -0.0001
Data Index: 697787 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2015. Min Range: -0.2015
Max Act: 0.1594. Min Act: -0.0001
Data Index: 1588822 (Python Code)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19