Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 795 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7792. Min Act: -0.0001
Data Index: 226174 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7940. Min Act: -0.0001
Data Index: 756914 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7603. Min Act: -0.0001
Data Index: 265517 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7423. Min Act: -0.0001
Data Index: 1659853 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7033. Min Act: -0.0001
Data Index: 841439 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7487. Min Act: -0.0001
Data Index: 1354468 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6716. Min Act: -0.0001
Data Index: 1529529 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7152. Min Act: -0.0001
Data Index: 1285611 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7122. Min Act: -0.0001
Data Index: 1942958 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6530. Min Act: -0.0001
Data Index: 1404562 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.7875. Min Act: -0.0001
Data Index: 1602437 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6506. Min Act: -0.0001
Data Index: 1698247 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6940. Min Act: -0.0001
Data Index: 747969 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.5914. Min Act: -0.0001
Data Index: 923131 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6353. Min Act: -0.0001
Data Index: 1188767 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6296. Min Act: -0.0001
Data Index: 220569 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6566. Min Act: -0.0001
Data Index: 859649 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6683. Min Act: -0.0001
Data Index: 828132 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6090. Min Act: -0.0001
Data Index: 871225 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7940. Min Range: -1.7940
Max Act: 1.6148. Min Act: -0.0001
Data Index: 1074853 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19