Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2134 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.5577. Min Act: -0.0001
Data Index: 1837507 (The Pile)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.4502. Min Act: -0.0001
Data Index: 33751 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.5219. Min Act: -0.0001
Data Index: 1598121 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3895. Min Act: -0.0001
Data Index: 470420 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.4689. Min Act: -0.0001
Data Index: 345742 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3841. Min Act: -0.0001
Data Index: 849575 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3395. Min Act: -0.0001
Data Index: 1785296 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3843. Min Act: -0.0001
Data Index: 1795904 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.2950. Min Act: -0.0001
Data Index: 459462 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3408. Min Act: -0.0001
Data Index: 1132896 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.2964. Min Act: -0.0001
Data Index: 1252268 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3550. Min Act: -0.0001
Data Index: 1973703 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3506. Min Act: -0.0001
Data Index: 1105691 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.2872. Min Act: -0.0001
Data Index: 1258318 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3530. Min Act: -0.0001
Data Index: 348806 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3768. Min Act: -0.0001
Data Index: 660217 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.3013. Min Act: -0.0001
Data Index: 1164720 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.2861. Min Act: -0.0001
Data Index: 639721 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.2481. Min Act: -0.0001
Data Index: 996463 (The Pile)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5577. Min Range: -1.5577
Max Act: 1.2500. Min Act: -0.0001
Data Index: 1012676 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19