Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2081 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0455. Min Act: -0.0001
Data Index: 1684600 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0455. Min Act: -0.0001
Data Index: 836169 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0455. Min Act: -0.0001
Data Index: 1702206 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0455. Min Act: -0.0001
Data Index: 1204021 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0455. Min Act: -0.0001
Data Index: 338659 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0455. Min Act: -0.0001
Data Index: 841444 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0455. Min Act: -0.0001
Data Index: 1349267 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.1089. Min Act: -0.0001
Data Index: 1015328 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.1089. Min Act: -0.0001
Data Index: 1858891 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.1089. Min Act: -0.0001
Data Index: 1189205 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.1089. Min Act: -0.0001
Data Index: 1131678 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.1089. Min Act: -0.0001
Data Index: 106517 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0709. Min Act: -0.0001
Data Index: 1415466 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0305. Min Act: -0.0001
Data Index: 1184835 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0305. Min Act: -0.0001
Data Index: 116260 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0305. Min Act: -0.0001
Data Index: 914449 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0305. Min Act: -0.0001
Data Index: 747806 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0305. Min Act: -0.0001
Data Index: 777540 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0305. Min Act: -0.0001
Data Index: 1066851 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1089. Min Range: -1.1089
Max Act: 1.0305. Min Act: -0.0001
Data Index: 1324539 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19