Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3452 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4859. Min Act: -0.0001
Data Index: 1076254 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4659. Min Act: -0.0001
Data Index: 579114 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4708. Min Act: -0.0001
Data Index: 451698 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4506. Min Act: -0.0001
Data Index: 1335729 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4524. Min Act: -0.0001
Data Index: 677072 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4312. Min Act: -0.0001
Data Index: 294699 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4136. Min Act: -0.0001
Data Index: 1706490 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4368. Min Act: -0.0001
Data Index: 1559017 (The Pile)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4203. Min Act: -0.0001
Data Index: 1943334 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4321. Min Act: -0.0001
Data Index: 1313740 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4135. Min Act: -0.0001
Data Index: 788930 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4122. Min Act: -0.0001
Data Index: 1330972 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4515. Min Act: -0.0001
Data Index: 834101 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4065. Min Act: -0.0001
Data Index: 1487014 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4087. Min Act: -0.0001
Data Index: 1191322 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4000. Min Act: -0.0001
Data Index: 218751 (The Pile)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4108. Min Act: -0.0001
Data Index: 1694003 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4257. Min Act: -0.0001
Data Index: 1056524 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.3953. Min Act: -0.0001
Data Index: 536506 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4859. Min Range: -0.4859
Max Act: 0.4024. Min Act: -0.0001
Data Index: 352340 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19