Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3694 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.0493. Min Range: -3.0493
Max Act: 3.0493. Min Act: -0.0001
Data Index: 9344 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.9679. Min Act: -0.0001
Data Index: 990861 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.3300. Min Act: -0.0001
Data Index: 748232 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.3974. Min Act: -0.0001
Data Index: 305979 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.7686. Min Act: -0.0001
Data Index: 310716 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.3709. Min Act: -0.0001
Data Index: 854451 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.3161. Min Act: -0.0001
Data Index: 845776 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.4350. Min Act: -0.0001
Data Index: 106480 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.4256. Min Act: -0.0001
Data Index: 123384 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.6865. Min Act: -0.0001
Data Index: 223741 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.4177. Min Act: -0.0001
Data Index: 714064 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.2688. Min Act: -0.0001
Data Index: 1069009 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.3589. Min Act: -0.0001
Data Index: 49023 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.0059. Min Act: -0.0001
Data Index: 1037662 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.1017. Min Act: -0.0001
Data Index: 255190 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.0438. Min Act: -0.0001
Data Index: 391868 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.1989. Min Act: -0.0001
Data Index: 1249124 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.1943. Min Act: -0.0001
Data Index: 370894 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.1741. Min Act: -0.0001
Data Index: 950418 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0493. Min Range: -3.0493
Max Act: 2.0446. Min Act: -0.0001
Data Index: 348043 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19