Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1396 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.8552. Min Act: -0.0001
Data Index: 542291 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7876. Min Act: -0.0001
Data Index: 1406335 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.8274. Min Act: -0.0001
Data Index: 1463279 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.8507. Min Act: -0.0000
Data Index: 82021 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7650. Min Act: -0.0000
Data Index: 984986 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7495. Min Act: -0.0001
Data Index: 1692642 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.6605. Min Act: -0.0001
Data Index: 1382516 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.8074. Min Act: -0.0001
Data Index: 1264396 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7480. Min Act: -0.0001
Data Index: 4455 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7231. Min Act: -0.0001
Data Index: 27439 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7252. Min Act: -0.0001
Data Index: 1697143 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7652. Min Act: -0.0000
Data Index: 1184812 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7146. Min Act: -0.0001
Data Index: 1640937 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7803. Min Act: -0.0001
Data Index: 1223898 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7276. Min Act: -0.0001
Data Index: 1164150 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.6963. Min Act: -0.0001
Data Index: 750954 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.6486. Min Act: -0.0001
Data Index: 764947 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.8099. Min Act: -0.0001
Data Index: 1571346 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7544. Min Act: -0.0001
Data Index: 1447955 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8552. Min Range: -0.8552
Max Act: 0.7520. Min Act: -0.0001
Data Index: 1465527 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19