Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3022 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.8808. Min Act: -0.0000
Data Index: 1329977 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.6479. Min Act: 0.0000
Data Index: 1962655 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.6276. Min Act: -0.0000
Data Index: 1186933 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.5793. Min Act: -0.0000
Data Index: 12658 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.5616. Min Act: -0.0000
Data Index: 1032695 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.5122. Min Act: -0.0000
Data Index: 1654036 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.3968. Min Act: 0.0000
Data Index: 411641 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.3861. Min Act: -0.0000
Data Index: 1267044 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2835. Min Act: -0.0000
Data Index: 1273256 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.3212. Min Act: 0.0000
Data Index: 259127 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2437. Min Act: -0.0000
Data Index: 290811 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.3106. Min Act: -0.0000
Data Index: 1942135 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.3099. Min Act: 0.0000
Data Index: 1178925 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2734. Min Act: -0.0000
Data Index: 939936 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2779. Min Act: 0.0000
Data Index: 1777500 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2503. Min Act: -0.0000
Data Index: 412930 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2301. Min Act: 0.0000
Data Index: 1612850 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2252. Min Act: -0.0000
Data Index: 782739 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.2642. Min Act: -0.0000
Data Index: 1977669 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8808. Min Range: -1.8808
Max Act: 1.1769. Min Act: 0.0000
Data Index: 1646437 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19