Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 857 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.8736. Min Act: -0.0001
Data Index: 1934188 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.5962. Min Act: -0.0001
Data Index: 1431621 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.5962. Min Act: -0.0001
Data Index: 1905337 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.5170. Min Act: -0.0001
Data Index: 200231 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.5170. Min Act: -0.0001
Data Index: 326222 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.4919. Min Act: -0.0001
Data Index: 1983881 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.5081. Min Act: -0.0001
Data Index: 613423 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.4167. Min Act: -0.0001
Data Index: 1603119 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.2282. Min Act: -0.0001
Data Index: 1890151 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.2282. Min Act: -0.0001
Data Index: 1633579 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.2356. Min Act: -0.0001
Data Index: 1984946 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.1188. Min Act: -0.0001
Data Index: 1245696 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.1059. Min Act: -0.0001
Data Index: 1678095 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.1059. Min Act: -0.0001
Data Index: 40532 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.1100. Min Act: -0.0001
Data Index: 794772 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.1638. Min Act: -0.0001
Data Index: 533737 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.0143. Min Act: -0.0001
Data Index: 1857898 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.0560. Min Act: -0.0001
Data Index: 540990 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.0388. Min Act: -0.0001
Data Index: 775447 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8736. Min Range: -1.8736
Max Act: 1.0424. Min Act: -0.0001
Data Index: 530784 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19