Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2348 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.7491. Min Act: -0.0001
Data Index: 1069184 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.6806. Min Act: -0.0001
Data Index: 1737188 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.6099. Min Act: -0.0001
Data Index: 130663 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.5789. Min Act: -0.0001
Data Index: 1867431 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.5249. Min Act: -0.0001
Data Index: 1176084 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.5142. Min Act: -0.0001
Data Index: 1057573 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.5645. Min Act: -0.0001
Data Index: 1460158 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.5341. Min Act: -0.0001
Data Index: 1391681 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.5173. Min Act: -0.0001
Data Index: 1199318 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4980. Min Act: -0.0001
Data Index: 619517 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.5133. Min Act: -0.0001
Data Index: 1803812 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4525. Min Act: -0.0001
Data Index: 1843256 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4715. Min Act: -0.0001
Data Index: 521124 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4692. Min Act: -0.0001
Data Index: 1281801 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4685. Min Act: -0.0001
Data Index: 756071 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4931. Min Act: -0.0001
Data Index: 545046 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4610. Min Act: -0.0001
Data Index: 1125858 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4752. Min Act: -0.0001
Data Index: 1446415 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4809. Min Act: -0.0001
Data Index: 1593569 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7491. Min Range: -0.7491
Max Act: 0.4552. Min Act: -0.0001
Data Index: 1605636 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19