Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2768 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0450. Min Act: -0.0001
Data Index: 284673 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0374. Min Act: -0.0001
Data Index: 212589 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0350. Min Act: -0.0001
Data Index: 1302534 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0350. Min Act: -0.0001
Data Index: 166789 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0350. Min Act: -0.0001
Data Index: 1503749 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0350. Min Act: -0.0001
Data Index: 1603450 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0348. Min Act: -0.0001
Data Index: 1061568 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0348. Min Act: -0.0001
Data Index: 1280337 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0348. Min Act: -0.0001
Data Index: 1897869 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0357. Min Act: -0.0001
Data Index: 575833 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0357. Min Act: -0.0000
Data Index: 1989384 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0357. Min Act: -0.0001
Data Index: 1858903 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0357. Min Act: -0.0000
Data Index: 1631210 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0357. Min Act: -0.0000
Data Index: 1359137 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0357. Min Act: -0.0001
Data Index: 329073 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0328. Min Act: -0.0001
Data Index: 10996 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0328. Min Act: -0.0000
Data Index: 128098 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0328. Min Act: -0.0001
Data Index: 401655 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0328. Min Act: -0.0001
Data Index: 129097 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0450. Min Range: -0.0450
Max Act: 0.0328. Min Act: -0.0001
Data Index: 386150 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19