Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 23 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.1309. Min Act: -0.0002
Data Index: 31187 (The Pile)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0929. Min Act: -0.0003
Data Index: 357735 (The Pile)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0935. Min Act: -0.0002
Data Index: 297792 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0899. Min Act: -0.0002
Data Index: 1198011 (The Pile)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0860. Min Act: -0.0002
Data Index: 1636948 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0822. Min Act: -0.0002
Data Index: 1456903 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0827. Min Act: -0.0002
Data Index: 555745 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0731. Min Act: -0.0002
Data Index: 875762 (The Pile)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0753. Min Act: -0.0002
Data Index: 557090 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0723. Min Act: -0.0002
Data Index: 301175 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0661. Min Act: -0.0002
Data Index: 1102538 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0658. Min Act: -0.0002
Data Index: 1869692 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0663. Min Act: -0.0002
Data Index: 1457794 (The Pile)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0639. Min Act: -0.0002
Data Index: 1218726 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0665. Min Act: -0.0002
Data Index: 1674499 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0652. Min Act: -0.0002
Data Index: 497441 (The Pile)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0628. Min Act: -0.0002
Data Index: 562619 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0608. Min Act: -0.0002
Data Index: 1570519 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0608. Min Act: -0.0002
Data Index: 432938 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1309. Min Range: -0.1309
Max Act: 0.0586. Min Act: -0.0002
Data Index: 1228504 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19