Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 660 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2832. Min Act: -0.0001
Data Index: 1139553 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2464. Min Act: -0.0001
Data Index: 1972092 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2658. Min Act: -0.0001
Data Index: 866884 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2489. Min Act: -0.0001
Data Index: 1906690 (The Pile)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2140. Min Act: -0.0001
Data Index: 1036709 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2082. Min Act: -0.0001
Data Index: 957519 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1966. Min Act: -0.0001
Data Index: 465086 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2021. Min Act: -0.0001
Data Index: 1835558 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1950. Min Act: -0.0001
Data Index: 349414 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1851. Min Act: -0.0001
Data Index: 748195 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1943. Min Act: -0.0001
Data Index: 1516165 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1945. Min Act: -0.0001
Data Index: 1308814 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1916. Min Act: -0.0001
Data Index: 1431502 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1800. Min Act: -0.0001
Data Index: 1302823 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.2009. Min Act: -0.0001
Data Index: 1048077 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1803. Min Act: -0.0001
Data Index: 1366609 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1820. Min Act: -0.0001
Data Index: 1270218 (The Pile)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1738. Min Act: -0.0001
Data Index: 21480 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1880. Min Act: -0.0001
Data Index: 122371 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2832. Min Range: -0.2832
Max Act: 0.1730. Min Act: -0.0001
Data Index: 73783 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19