Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 984 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.2348. Min Act: -0.0001
Data Index: 1356030 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.2106. Min Act: -0.0001
Data Index: 362946 (The Pile)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.2078. Min Act: -0.0001
Data Index: 514184 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1900. Min Act: -0.0001
Data Index: 1851350 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1957. Min Act: -0.0001
Data Index: 1621896 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1848. Min Act: -0.0001
Data Index: 137626 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1905. Min Act: -0.0001
Data Index: 1191780 (The Pile)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.2035. Min Act: -0.0001
Data Index: 1273962 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1969. Min Act: -0.0001
Data Index: 1594021 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1848. Min Act: -0.0001
Data Index: 1780138 (The Pile)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1698. Min Act: -0.0001
Data Index: 810507 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1819. Min Act: -0.0001
Data Index: 1176063 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1830. Min Act: -0.0001
Data Index: 1471354 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1841. Min Act: -0.0001
Data Index: 1356264 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1702. Min Act: -0.0001
Data Index: 1411930 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1817. Min Act: -0.0001
Data Index: 1170977 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1713. Min Act: -0.0001
Data Index: 83398 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1699. Min Act: -0.0001
Data Index: 576522 (The Pile)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1703. Min Act: -0.0001
Data Index: 997186 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2348. Min Range: -0.2348
Max Act: 0.1692. Min Act: -0.0001
Data Index: 565065 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19