Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1555 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0442. Min Act: -0.0003
Data Index: 258616 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0299. Min Act: -0.0003
Data Index: 1580698 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0270. Min Act: -0.0003
Data Index: 881459 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 53016 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 52910 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0002
Data Index: 21244 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 19852 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 52514 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 31634 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0002
Data Index: 50403 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 48633 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 48418 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0002
Data Index: 4389 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 1077 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 2573 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 18787 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0002
Data Index: 2385 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 44223 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 4314 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0442. Min Range: -0.0442
Max Act: 0.0247. Min Act: -0.0003
Data Index: 38684 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19