Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1106 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.9709. Min Act: -0.0001
Data Index: 1885935 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.3064. Min Act: -0.0001
Data Index: 1000905 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0960. Min Act: -0.0001
Data Index: 1457641 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.1452. Min Act: -0.0001
Data Index: 1926397 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0011. Min Act: -0.0001
Data Index: 1200597 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.3105. Min Act: -0.0001
Data Index: 207465 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.3653. Min Act: -0.0001
Data Index: 335082 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.1106. Min Act: -0.0001
Data Index: 263001 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.2653. Min Act: -0.0001
Data Index: 111050 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0561. Min Act: -0.0001
Data Index: 1663314 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.1853. Min Act: -0.0001
Data Index: 1287033 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0498. Min Act: -0.0001
Data Index: 1447185 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0867. Min Act: -0.0001
Data Index: 647876 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0918. Min Act: -0.0002
Data Index: 340614 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.1742. Min Act: -0.0001
Data Index: 439834 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0926. Min Act: -0.0001
Data Index: 684933 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.0322. Min Act: -0.0001
Data Index: 642438 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.1496. Min Act: -0.0001
Data Index: 122566 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.1959. Min Act: -0.0001
Data Index: 1435044 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9709. Min Range: -1.9709
Max Act: 1.1909. Min Act: -0.0001
Data Index: 1090135 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19