Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2221 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.1571. Min Act: -0.0001
Data Index: 1856629 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.1240. Min Act: -0.0001
Data Index: 306420 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.1181. Min Act: -0.0001
Data Index: 1031243 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.1135. Min Act: -0.0001
Data Index: 1581626 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.1403. Min Act: -0.0001
Data Index: 1920999 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.0643. Min Act: -0.0001
Data Index: 1009343 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.1837. Min Act: -0.0001
Data Index: 1494184 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.1304. Min Act: -0.0001
Data Index: 277361 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.0320. Min Act: -0.0001
Data Index: 1834072 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.0085. Min Act: -0.0001
Data Index: 1866934 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.0073. Min Act: -0.0001
Data Index: 105217 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.0228. Min Act: -0.0001
Data Index: 1990160 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1837. Min Range: -1.1837
Max Act: 0.9187. Min Act: -0.0001
Data Index: 1804155 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1837. Min Range: -1.1837
Max Act: 0.9560. Min Act: -0.0001
Data Index: 90595 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1837. Min Range: -1.1837
Max Act: 0.9821. Min Act: -0.0001
Data Index: 1919015 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1837. Min Range: -1.1837
Max Act: 1.0108. Min Act: -0.0001
Data Index: 278146 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1837. Min Range: -1.1837
Max Act: 0.9409. Min Act: -0.0001
Data Index: 12359 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1837. Min Range: -1.1837
Max Act: 0.9093. Min Act: -0.0001
Data Index: 893063 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1837. Min Range: -1.1837
Max Act: 0.9598. Min Act: -0.0001
Data Index: 1513739 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1837. Min Range: -1.1837
Max Act: 0.9158. Min Act: -0.0001
Data Index: 840555 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19