Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 866 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.7059. Min Act: -0.0001
Data Index: 1093275 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.3876. Min Act: -0.0001
Data Index: 63673 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.1764. Min Act: -0.0001
Data Index: 70541 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.2159. Min Act: -0.0001
Data Index: 1689126 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.4007. Min Act: -0.0001
Data Index: 1969525 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.3641. Min Act: -0.0001
Data Index: 16546 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.4640. Min Act: -0.0001
Data Index: 1136048 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.3323. Min Act: -0.0001
Data Index: 154970 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.8510. Min Act: -0.0001
Data Index: 1729727 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.0183. Min Act: -0.0001
Data Index: 1546661 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8510. Min Range: -2.8510
Max Act: 1.5460. Min Act: -0.0001
Data Index: 829957 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.4451. Min Act: -0.0001
Data Index: 683693 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.1291. Min Act: -0.0001
Data Index: 1849343 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.3952. Min Act: -0.0001
Data Index: 1904599 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8510. Min Range: -2.8510
Max Act: 1.8910. Min Act: -0.0001
Data Index: 1879399 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.1117. Min Act: -0.0001
Data Index: 1903787 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.2751. Min Act: -0.0001
Data Index: 13783 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.6662. Min Act: -0.0001
Data Index: 1161913 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.5583. Min Act: -0.0001
Data Index: 1116061 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8510. Min Range: -2.8510
Max Act: 2.2374. Min Act: -0.0001
Data Index: 440777 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19