Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 904 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.1885. Min Range: -3.1885
Max Act: 3.1885. Min Act: -0.0001
Data Index: 50221 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.2097. Min Act: -0.0001
Data Index: 1593688 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.3467. Min Act: -0.0001
Data Index: 1802047 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.4474. Min Act: -0.0001
Data Index: 281196 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.1645. Min Act: -0.0001
Data Index: 1758721 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.1849. Min Act: -0.0001
Data Index: 1896100 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.1627. Min Act: -0.0001
Data Index: 436956 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.1933. Min Act: -0.0001
Data Index: 1892003 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.0558. Min Act: -0.0001
Data Index: 1495070 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.1724. Min Act: -0.0002
Data Index: 1914373 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.1513. Min Act: -0.0001
Data Index: 867770 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.9867. Min Act: -0.0001
Data Index: 170336 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.8214. Min Act: -0.0001
Data Index: 1982771 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.8257. Min Act: -0.0001
Data Index: 413335 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1885. Min Range: -3.1885
Max Act: 2.0884. Min Act: -0.0001
Data Index: 1136557 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.9056. Min Act: -0.0001
Data Index: 1532755 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.8210. Min Act: -0.0001
Data Index: 1445880 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.9028. Min Act: -0.0001
Data Index: 1263028 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.9296. Min Act: -0.0001
Data Index: 766844 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1885. Min Range: -3.1885
Max Act: 1.9157. Min Act: -0.0001
Data Index: 1535429 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19