Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 2047 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.8092. Min Act: -0.0005
Data Index: 1987907 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.8150. Min Act: -0.0004
Data Index: 354678 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7412. Min Act: -0.0004
Data Index: 1462758 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7697. Min Act: -0.0004
Data Index: 627192 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7667. Min Act: -0.0005
Data Index: 1080944 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7390. Min Act: -0.0004
Data Index: 83386 (The Pile)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7562. Min Act: -0.0004
Data Index: 1342329 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7530. Min Act: -0.0004
Data Index: 1421135 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7312. Min Act: -0.0004
Data Index: 802723 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7459. Min Act: -0.0004
Data Index: 14921 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.6969. Min Act: -0.0004
Data Index: 678249 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7050. Min Act: -0.0004
Data Index: 1019142 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.6951. Min Act: -0.0004
Data Index: 604257 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.6932. Min Act: -0.0004
Data Index: 1652760 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.6676. Min Act: -0.0004
Data Index: 48811 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7130. Min Act: -0.0004
Data Index: 58577 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7068. Min Act: -0.0004
Data Index: 624754 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7307. Min Act: -0.0004
Data Index: 1636641 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.6876. Min Act: -0.0004
Data Index: 696716 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8150. Min Range: -0.8150
Max Act: 0.7071. Min Act: -0.0004
Data Index: 1288982 (The Pile)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19