Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1305 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.8365. Min Act: -0.0001
Data Index: 896287 (The Pile)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.7246. Min Act: -0.0001
Data Index: 971923 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.7737. Min Act: -0.0001
Data Index: 1909642 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6999. Min Act: -0.0001
Data Index: 1890553 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6834. Min Act: -0.0001
Data Index: 473086 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6321. Min Act: -0.0001
Data Index: 1361547 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.7323. Min Act: -0.0001
Data Index: 1179992 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6738. Min Act: -0.0001
Data Index: 1112149 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.7526. Min Act: -0.0001
Data Index: 581868 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6742. Min Act: -0.0001
Data Index: 1122488 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6730. Min Act: -0.0001
Data Index: 419331 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6730. Min Act: -0.0001
Data Index: 849348 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6730. Min Act: -0.0001
Data Index: 586123 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6730. Min Act: -0.0001
Data Index: 720038 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6730. Min Act: -0.0001
Data Index: 1666892 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.5893. Min Act: -0.0001
Data Index: 643244 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6298. Min Act: -0.0001
Data Index: 1719584 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.7324. Min Act: -0.0001
Data Index: 998491 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6164. Min Act: -0.0001
Data Index: 1922515 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8365. Min Range: -0.8365
Max Act: 0.6811. Min Act: -0.0001
Data Index: 1055167 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19