Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 661 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0925. Min Act: -0.0001
Data Index: 1317280 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0096. Min Act: -0.0001
Data Index: 437013 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0349. Min Act: -0.0001
Data Index: 1365452 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.9952. Min Act: -0.0001
Data Index: 1729912 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0063. Min Act: -0.0001
Data Index: 868846 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0774. Min Act: -0.0001
Data Index: 1518232 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.9748. Min Act: -0.0001
Data Index: 664905 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0131. Min Act: -0.0001
Data Index: 809816 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0256. Min Act: -0.0001
Data Index: 552840 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0812. Min Act: -0.0001
Data Index: 453730 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0126. Min Act: -0.0001
Data Index: 958218 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.8923. Min Act: -0.0001
Data Index: 113363 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.8627. Min Act: -0.0001
Data Index: 266990 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0994. Min Act: -0.0001
Data Index: 202753 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.9324. Min Act: -0.0001
Data Index: 1319699 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.9911. Min Act: -0.0001
Data Index: 906004 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0994. Min Range: -1.0994
Max Act: 1.0152. Min Act: -0.0001
Data Index: 1184006 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.9920. Min Act: -0.0001
Data Index: 740376 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.9450. Min Act: -0.0001
Data Index: 385483 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0994. Min Range: -1.0994
Max Act: 0.9374. Min Act: -0.0001
Data Index: 358932 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19