Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2335 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.5009. Min Act: -0.0000
Data Index: 831113 (The Pile)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.4044. Min Act: -0.0000
Data Index: 664268 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.2540. Min Act: -0.0000
Data Index: 1177727 (The Pile)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.3206. Min Act: 0.0001
Data Index: 1615397 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.3763. Min Act: -0.0000
Data Index: 1258698 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.2700. Min Act: 0.0000
Data Index: 1270561 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.2619. Min Act: -0.0000
Data Index: 1418462 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.2080. Min Act: 0.0001
Data Index: 1760936 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1986. Min Act: -0.0000
Data Index: 558825 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1097. Min Act: -0.0000
Data Index: 1462593 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1552. Min Act: -0.0000
Data Index: 699372 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1443. Min Act: -0.0000
Data Index: 1171012 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1440. Min Act: -0.0000
Data Index: 866255 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1289. Min Act: -0.0000
Data Index: 613087 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1329. Min Act: -0.0000
Data Index: 321191 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1025. Min Act: -0.0000
Data Index: 375012 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1138. Min Act: 0.0000
Data Index: 1955866 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.1027. Min Act: -0.0000
Data Index: 1317805 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.0841. Min Act: -0.0000
Data Index: 1572863 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5009. Min Range: -1.5009
Max Act: 1.0934. Min Act: -0.0000
Data Index: 840386 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19