Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1615 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.9862. Min Act: -0.0000
Data Index: 166464 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.8162. Min Act: -0.0000
Data Index: 169127 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.8198. Min Act: -0.0000
Data Index: 687721 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.6323. Min Act: -0.0000
Data Index: 434546 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.5179. Min Act: -0.0000
Data Index: 734597 (The Pile)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.9802. Min Act: -0.0000
Data Index: 1110079 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.1871. Min Act: -0.0000
Data Index: 370612 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.8735. Min Act: -0.0000
Data Index: 490814 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.0607. Min Act: -0.0000
Data Index: 1360604 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.0094. Min Act: -0.0000
Data Index: 845857 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.0231. Min Act: -0.0000
Data Index: 361934 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.8779. Min Act: -0.0000
Data Index: 239529 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.1828. Min Act: -0.0000
Data Index: 12232 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.9618. Min Act: -0.0000
Data Index: 938616 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.9758. Min Act: -0.0000
Data Index: 1114493 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.0688. Min Act: -0.0000
Data Index: 868363 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9862. Min Range: -2.9862
Max Act: 2.1749. Min Act: -0.0000
Data Index: 1262467 (The Pile)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.7611. Min Act: -0.0000
Data Index: 1617776 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.9543. Min Act: -0.0000
Data Index: 1755509 (The Pile)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9862. Min Range: -2.9862
Max Act: 1.9345. Min Act: -0.0000
Data Index: 892038 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19