Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1654 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.1832. Min Act: -0.0001
Data Index: 1540393 (The Pile)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.1080. Min Act: -0.0001
Data Index: 1867170 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.1507. Min Act: -0.0001
Data Index: 1471184 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0737. Min Act: -0.0001
Data Index: 788767 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.2786. Min Act: -0.0001
Data Index: 1414314 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.2383. Min Act: -0.0001
Data Index: 172650 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.1678. Min Act: -0.0001
Data Index: 210186 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.2340. Min Act: -0.0001
Data Index: 549994 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.1030. Min Act: -0.0001
Data Index: 55667 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0662. Min Act: -0.0001
Data Index: 1765586 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2786. Min Range: -1.2786
Max Act: 0.9697. Min Act: -0.0001
Data Index: 1043177 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.1472. Min Act: -0.0001
Data Index: 1709331 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0837. Min Act: -0.0001
Data Index: 114653 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0229. Min Act: -0.0001
Data Index: 627483 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.1877. Min Act: -0.0001
Data Index: 202411 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0854. Min Act: -0.0001
Data Index: 1764451 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0394. Min Act: -0.0001
Data Index: 1606753 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.2653. Min Act: -0.0001
Data Index: 1329013 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0911. Min Act: -0.0001
Data Index: 1670993 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2786. Min Range: -1.2786
Max Act: 1.0104. Min Act: -0.0001
Data Index: 480145 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19